© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 140182
    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_37_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
     SUM
    0.39
     எலும்
    0.39
    essoas
    0.38
    adito
    0.38
     Hoss
    0.37
    長さ
    0.36
    Alcohol
    0.36
    alcohol
    0.35
    細
    0.35
    izada
    0.35
    POSITIVE LOGITS
     хватает
    0.39
     genoeg
    0.39
    予想
    0.38
     seraient
    0.38
     feared
    0.37
     Méd
    0.37
     notoriously
    0.37
     Formerly
    0.37
     Includes
    0.36
     पर्याप्त
    0.36
    Activations Density 0.000%

    No Known Activations