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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91676
    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_11_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
    لا
    0.52
    !,
    0.48
     Inspe
    0.47
     Penalty
    0.47
    B
    0.46
     &/
    0.46
    ेंट
    0.45
     Altern
    0.45
     +,
    0.45
    LA
    0.45
    POSITIVE LOGITS
     windowsill
    0.57
     preguntó
    0.50
     rulemaking
    0.48
     químicas
    0.48
     Христо
    0.47
    ydi
    0.47
    WebServer
    0.46
    ному
    0.46
    cdf
    0.45
     sawdust
    0.44
    Activations Density 0.000%

    No Known Activations