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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 228699
    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_57_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
     enforce
    0.38
     enforced
    0.38
     enforces
    0.37
     marcas
    0.36
    ः
    0.36
    Exec
    0.36
     പക്ഷ
    0.35
    勍
    0.35
     pyro
    0.34
    बन
    0.34
    POSITIVE LOGITS
    urin
    0.38
    argu
    0.36
    änn
    0.36
    undy
    0.36
    ступа
    0.35
     sepsis
    0.35
    াদুর
    0.35
    вена
    0.35
    HUN
    0.35
     blazer
    0.35
    Activations Density 0.000%

    No Known Activations