© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 102742
    Prev
    Next
    INDEX
    Explanations

    list item, index, option, table, loading, submit, login, drawer

    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_14_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ت
    0.79
    t
    0.76
    T
    0.66
    ס
    0.66
    س
    0.64
    Т
    0.63
    ال
    0.61
    ต
    0.61
    ת
    0.60
    স
    0.57
    POSITIVE LOGITS
     théâtre
    0.59
     collegiate
    0.56
     escolares
    0.56
     Và
    0.56
     eterna
    0.55
    elessly
    0.54
     గారి
    0.54
     jubilee
    0.53
     escola
    0.53
     आस्था
    0.53
    Activations Density 0.001%

    No Known Activations