© 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. 29198
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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
    š
    0.61
    ГА
    0.60
    uj
    0.56
    ځ
    0.56
    \
    0.56
     ಪದ
    0.55
    眄
    0.55
    qst
    0.54
    ans
    0.53
    حال
    0.53
    POSITIVE LOGITS
    ،
    0.88
    。
    0.86
    ।
    0.70
     on
    0.65
    ，
    0.64
    g
    0.62
    ারের
    0.61
    volvimento
    0.61
    );
    0.59
     ,
    0.59
    Activations Density 0.016%

    No Known Activations