© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 198964
    Prev
    Next
    INDEX
    Explanations

    increasingly popular or common

    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_4_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
     ବି
    0.55
    𖥔
    0.53
     ۷
    0.52
    ᆸ
    0.52
    र्मेंद्र
    0.50
     ۸
    0.50
    𝗙
    0.50
     Appropriations
    0.50
     उत्पादन
    0.49
     Бі
    0.49
    POSITIVE LOGITS
    $
    0.59
     $
    0.53
    -
    0.52
    ’
    0.50
    3
    0.48
     declared
    0.47
    2
    0.46
     (
    0.44
    دان
    0.44
    1
    0.44
    Activations Density 0.000%

    No Known Activations