© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41187
    Prev
    Next
    INDEX
    Explanations

    based on race

    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_22_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
     જરૂર
    0.24
     voda
    0.24
    ẞ
    0.23
    आव
    0.23
    犹豫
    0.23
     erforder
    0.23
     বনে
    0.23
    CellStyle
    0.22
     Archaeological
    0.22
    人生
    0.22
    POSITIVE LOGITS
    綬
    0.27
    넛
    0.27
    thirds
    0.27
     акчага
    0.27
     बिंदु
    0.26
     huit
    0.26
    に対し
    0.25
     illegal
    0.25
    在我
    0.25
     ವೇಳೆ
    0.25
    Activations Density 0.003%

    No Known Activations