© 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. 85383
    Prev
    Next
    INDEX
    Explanations

    run as administrator

    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
    _
    0.83
    {
    0.82
    for
    0.80
    *
    0.77
    [
    0.69
    tor
    0.68
    2
    0.68
    '
    0.68
    ..
    0.64
    (
    0.63
    POSITIVE LOGITS
    یت
    0.84
    은
    0.80
    يل
    0.78
     running
    0.77
    व
    0.76
    ット
    0.75
    ید
    0.75
    을
    0.73
     a
    0.71
     on
    0.71
    Activations Density 0.001%

    No Known Activations