© 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. 33373
    Prev
    Next
    INDEX
    Explanations

    .io, city, Hollow, DeFronzo

    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
    ის
    0.65
    ية
    0.64
    of
    0.63
    ంగా
    0.59
    м
    0.59
    یت
    0.58
    ى
    0.58
    ichtet
    0.55
    र्मेंद्र
    0.55
    as
    0.55
    POSITIVE LOGITS
    ang
    0.92
    AG
    0.83
     for
    0.78
    IS
    0.74
    udah
    0.73
    H
    0.73
    ED
    0.72
    IM
    0.70
    ানার
    0.68
    unki
    0.67
    Activations Density 0.008%

    No Known Activations