© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107057
    Prev
    Next
    INDEX
    Explanations

    about following common phrases

    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_2_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
    '
    1.24
     was
    1.15
     않
    1.00
     જ
    0.95
     шесть
    0.95
     않은
    0.93
     بیش
    0.91
     ની
    0.90
     ਖ
    0.90
    いました
    0.89
    POSITIVE LOGITS
    ك
    1.70
    و
    1.53
    ע
    1.35
    ل
    1.34
    h
    1.32
    ع
    1.30
    要
    1.30
    k
    1.28
    ه
    1.26
    ح
    1.26
    Activations Density 0.003%

    No Known Activations