© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 232892
    Prev
    Next
    INDEX
    Explanations

    markers

    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_6_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
    ;
    1.25
    '
    1.09
    >
    1.07
    %
    0.96
    _
    0.94
     एवं
    0.86
    െ
    0.86
    m
    0.86
    <0x80>
    0.84
    กัน
    0.83
    POSITIVE LOGITS
    в
    0.92
    ați
    0.88
    inį
    0.82
    బ్ర
    0.80
    a
    0.79
    been
    0.78
    ítico
    0.77
    ᱶ
    0.77
    prés
    0.76
    ၷ
    0.76
    Activations Density 0.000%

    No Known Activations