© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 109155
    Prev
    Next
    INDEX
    Explanations

    return values

    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_1_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
    s
    1.70
     in
    1.66
    p
    1.62
    ب
    1.60
    re
    1.59
    us
    1.57
    t
    1.57
    on
    1.56
    is
    1.53
    to
    1.45
    POSITIVE LOGITS
     practitioner
    0.98
     tambour
    0.94
    ꯠ
    0.94
     pousse
    0.93
    <0x97>
    0.92
    انه
    0.88
    <0x91>
    0.88
    :
    0.88
     distillery
    0.86
     marketplace
    0.85
    Activations Density 0.007%

    No Known Activations