© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 217406
    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_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Production
    0.39
     ሶ
    0.38
    Churn
    0.36
    avio
    0.36
    cerpt
    0.35
     एस
    0.34
    Minimum
    0.34
    S
    0.34
    обо
    0.34
    ceived
    0.33
    POSITIVE LOGITS
     Dryden
    0.40
    द्द
    0.40
     PGR
    0.39
    FIL
    0.38
    FZ
    0.38
     Stephan
    0.38
    лина
    0.38
     fazem
    0.38
    GR
    0.38
    ண்ட்
    0.37
    Activations Density 0.000%

    No Known Activations