© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 46949
    Prev
    Next
    INDEX
    Explanations

    aggression

    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_10_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
    .
    0.82
    h
    0.71
      
    0.70
    b
    0.68
     nhàng
    0.67
    vara
    0.67
     นาที
    0.66
    brahim
    0.66
    ver
    0.65
    bc
    0.65
    POSITIVE LOGITS
    та
    0.91
    ن
    0.88
    ش
    0.77
    น
    0.77
    두
    0.76
    ш
    0.75
    은
    0.75
    کل
    0.74
    νό
    0.73
    Да
    0.72
    Activations Density 0.006%

    No Known Activations