© 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. 41208
    Prev
    Next
    INDEX
    Explanations

    men and women populations

    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
    STATS
    0.50
    bestroute
    0.44
    씌
    0.44
    UNIVERS
    0.43
    FREQ
    0.42
    STTS
    0.42
    鬯
    0.42
    status
    0.41
    +%
    0.41
    জিওথের
    0.40
    POSITIVE LOGITS
     ล
    0.43
    詳細
    0.41
     Hyatt
    0.41
     Wię
    0.40
    અ
    0.40
     Courtney
    0.39
     দল
    0.39
     captivated
    0.38
    ដំណើរ
    0.38
     ส่ง
    0.38
    Activations Density 0.002%

    No Known Activations