© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84915
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_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
    ся
    0.77
    ﺯ
    0.76
    надцать
    0.75
     capucha
    0.75
    ﻋ
    0.74
    ない
    0.69
    ﺱ
    0.67
    ຕໍ່
    0.66
    ニック
    0.65
    перед
    0.65
    POSITIVE LOGITS
     in
    0.83
     de
    0.75
     <=
    0.69
     an
    0.60
    esc
    0.56
    at
    0.54
     ind
    0.54
    Garden
    0.52
    ull
    0.52
    Have
    0.50
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.