© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 241485
    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_40_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
     rept
    0.42
    SSS
    0.38
    疟
    0.37
     Scattered
    0.36
    EMPTY
    0.36
     ब्रांच
    0.36
     striis
    0.36
     hora
    0.35
    遇到了
    0.34
    ="/"
    0.34
    POSITIVE LOGITS
     অক্সিজ
    0.41
    өт
    0.38
    owią
    0.36
     significativo
    0.36
     Sauer
    0.35
     নামাজ
    0.35
     Algonquin
    0.35
    FindAsync
    0.35
    resents
    0.34
    typeName
    0.34
    Activations Density 0.000%

    No Known Activations