© 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. 39923
    Prev
    Next
    INDEX
    Explanations

    napalm

    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
    n
    0.89
    h
    0.82
    νη
    0.81
    не
    0.80
    ن
    0.78
    m
    0.77
    ди
    0.73
    ку
    0.73
    دی
    0.73
    み
    0.72
    POSITIVE LOGITS
    O
    0.76
    <0x0D>
    0.72
    ak
    0.71
     Василий
    0.61
     mille
    0.61
    (
    0.60
    า
    0.59
    assador
    0.58
    ית
    0.57
    adito
    0.57
    Activations Density 0.004%

    No Known Activations