e2b
Datasets
All datasets matching “e2b”gemma-4-e2b-atlas
gemma-4-e2b-it-atlasgemma-4-E2B-it-pi-mono-agent-evalgemma4-bestckpt-traces-topk128-v2-e2b-mediumgemma-4-E2B-it-pi-mono-agent-loss-fpgemma-4-e2b-it-SAE
gemma-4-e2b-it — 35-layer SAE atlas
Sparse autoencoders on every decoder layer of gemma-4-e2b-it. Trained from scratch in one rolling pipeline with an event-aware controller. 35 layers, 49,152 features per layer, no per-layer hand-tuning.
The base model is a stubborn one. 15 sliding-window layers, then BAM no KV cache, thick and getting thicker the deeper you go. This atlas was built the whole way through it anyway.
What this is
Three months of work. My first… See the full description on the dataset page: https://huggingface.co/datasets/juiceb0xc0de/gemma-4-e2b-it-SAE.
