© 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. 127913
    Prev
    Next
    INDEX
    Explanations

    `I. Introduction` headings

    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
    '
    1.17
    :
    1.02
    ’
    0.93
    [
    0.87
    +
    0.77
    *
    0.76
    .
    0.74
     in
    0.73
    ru
    0.73
    ,
    0.73
    POSITIVE LOGITS
    да
    0.99
    ید
    0.82
    ется
    0.81
    онер
    0.78
    ة
    0.77
    িলার
    0.75
    一つの
    0.75
    инг
    0.75
    માં
    0.74
     tradiz
    0.74
    Activations Density 0.001%

    No Known Activations