© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 211602
    Prev
    Next
    INDEX
    Explanations

    fats metabolized

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ია
    0.41
     minorities
    0.40
     villages
    0.40
    \"]
    0.39
    isure
    0.39
     adjourned
    0.38
    青
    0.38
     छुट्टी
    0.38
     littered
    0.38
    无穷
    0.38
    POSITIVE LOGITS
    SerializeField
    0.44
    곁
    0.42
    шов
    0.41
     стан
    0.39
     necesitan
    0.39
    탠
    0.39
    Walls
    0.38
     தொகுதி
    0.38
    Esta
    0.38
     zid
    0.38
    Activations Density 0.001%

    No Known Activations