© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 123419
    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_37_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
     brokers
    0.38
    冲
    0.38
    評論
    0.37
     未
    0.37
    ኪ
    0.36
    충
    0.35
     associate
    0.35
     broker
    0.35
    liquibase
    0.34
    achet
    0.34
    POSITIVE LOGITS
    羸
    0.39
     dignit
    0.38
    .??.??"]
    0.38
     proz
    0.38
    犄
    0.38
    নান
    0.38
    
    0.37
     verticale
    0.37
     illo
    0.37
    alaman
    0.37
    Activations Density 0.000%

    No Known Activations