© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 129204
    Prev
    Next
    INDEX
    Explanations

    decision making or trees

    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_6_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
    on
    1.56
    m
    1.37
    en
    1.36
    is
    1.33
    p
    1.16
    al
    1.14
    il
    1.10
    ن
    1.09
    ,
    1.05
    _
    0.97
    POSITIVE LOGITS
     केल्यानंतर
    0.88
     Vào
    0.87
    ắc
    0.86
    два
    0.80
     ಯಾ
    0.80
     Eğitim
    0.79
     ಆದರೆ
    0.78
     Сен
    0.77
     Đến
    0.77
     Пользова
    0.77
    Activations Density 0.003%

    No Known Activations