© 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. 40894
    Prev
    Next
    INDEX
    Explanations

    French influence on English

    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
    ∓
    0.74
    0
    0.70
    us
    0.70
    ون
    0.65
    <0x80>
    0.64
    xp
    0.60
    ps
    0.59
     ярко
    0.59
    kmeans
    0.58
    v
    0.57
    POSITIVE LOGITS
    m
    0.77
    न
    0.71
    ม
    0.71
    ni
    0.70
    ブ
    0.68
    ní
    0.67
    ني
    0.67
    mo
    0.64
     it
    0.64
    มูล
    0.63
    Activations Density 0.001%

    No Known Activations