© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 47339
    Prev
    Next
    INDEX
    Explanations

    бодрящий bodyguard

    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_3_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
    ।
    0.88
    8
    0.82
    ,"
    0.76
    ،
    0.73
    ,’’
    0.73
    ug
    0.70
    *
    0.66
    غ
    0.65
    anding
    0.64
     می‌توان
    0.64
    POSITIVE LOGITS
    o
    0.93
    d
    0.91
    y
    0.89
    t
    0.85
    c
    0.84
    en
    0.80
    e
    0.76
    in
    0.70
    最
    0.70
    kende
    0.68
    Activations Density 0.003%

    No Known Activations