© 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. 19307
    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
     motivational
    0.34
     посу
    0.31
    ২
    0.31
    attrib
    0.30
     otk
    0.29
     கெல்
    0.29
    Ŕ
    0.29
     br
    0.29
     Mest
    0.29
     উদ্
    0.29
    POSITIVE LOGITS
    人之
    0.35
    我想
    0.35
     Installations
    0.33
    elry
    0.32
    placement
    0.32
     Elsewhere
    0.32
    ädt
    0.31
    nings
    0.31
    改编
    0.31
    [][
    0.30
    Activations Density 0.004%

    No Known Activations