© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173888
    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_20_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
     that
    0.73
     in
    0.72
     with
    0.56
     Dé
    0.55
     That
    0.53
     bei
    0.52
     a
    0.52
    æ
    0.50
     an
    0.49
     Dinosaur
    0.49
    POSITIVE LOGITS
    Strafpunkte
    0.52
    ناو
    0.52
    йдз
    0.52
     اوپر
    0.51
    ufieurs
    0.51
     ವಿಧಾನಸ
    0.51
    getMainUI
    0.50
    sources
    0.50
    جور
    0.49
    xgb
    0.49
    Activations Density 0.000%

    No Known Activations