© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 225283
    Prev
    Next
    INDEX
    Explanations

    model_selection import

    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_10_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
     ۷
    0.75
    ,
    0.74
    нков
    0.70
    ๗
    0.69
    نسان
    0.68
    又は
    0.67
    ти
    0.66
     ولم
    0.65
    ７
    0.64
    ‌شده
    0.63
    POSITIVE LOGITS
     for
    1.03
     if
    0.81
     when
    0.75
     from
    0.71
     find
    0.67
     state
    0.66
    tank
    0.65
     delve
    0.64
     BIG
    0.64
     WHEN
    0.64
    Activations Density 0.001%

    No Known Activations