© 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. 121607
    Prev
    Next
    INDEX
    Explanations

    all French and Spanish plurals

    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
    ld
    0.68
    3
    0.61
     essais
    0.59
    ty
    0.59
     ।
    0.59
    teurs
    0.59
    У
    0.58
    🚘
    0.58
    rict
    0.57
    rs
    0.57
    POSITIVE LOGITS
    '
    0.86
    ت
    0.86
    س
    0.86
    لنا
    0.81
    ناك
    0.73
    تون
    0.73
    <0x80>
    0.72
    uş
    0.72
    ిన
    0.71
    αν
    0.71
    Activations Density 0.003%

    No Known Activations