© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 51530
    Prev
    Next
    INDEX
    Explanations

    exclamations and extended sounds

    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
    و
    0.73
    不
    0.72
    crash
    0.66
    Klik
    0.63
    Binding
    0.62
    o
    0.61
    chuk
    0.61
    visitor
    0.60
    voor
    0.60
    oğlu
    0.60
    POSITIVE LOGITS
    ä
    0.89
     on
    0.78
    à
    0.77
    л
    0.76
    いた
    0.75
    ل
    0.71
    ها
    0.70
     in
    0.69
    agons
    0.68
    ě
    0.68
    Activations Density 0.002%

    No Known Activations