© 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. 39785
    Prev
    Next
    INDEX
    Explanations

    traffic control and safety measures

    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
    Not in Any Lists

    No Comments

    Negative Logits
     demons
    0.69
    ам
    0.63
     punishments
    0.63
     midfielders
    0.61
     创建
    0.61
     ആൻ
    0.61
     F
    0.60
    ढ़े
    0.60
     upholding
    0.60
    Ꭱ
    0.60
    POSITIVE LOGITS
    is
    0.97
    ية
    0.81
    ing
    0.77
    ة
    0.74
    are
    0.68
    isinin
    0.68
    lane
    0.64
    zelfde
    0.64
    lene
    0.64
    ির
    0.63
    Activations Density 0.008%

    No Known Activations