© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 834
    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_39_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
    Performed
    0.32
    ív
    0.28
    Perform
    0.28
     Archaeology
    0.27
     clout
    0.27
    ucine
    0.27
    {-
    0.27
    *}
    0.27
     ém
    0.27
    bau
    0.26
    POSITIVE LOGITS
     событий
    0.38
     događ
    0.30
    ｣
    0.30
     eventos
    0.30
    斤
    0.30
    aggo
    0.29
    ध्
    0.29
     goddesses
    0.29
    舌
    0.29
     subpo
    0.29
    Activations Density 0.033%

    No Known Activations