© 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. 228678
    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
    ="#!"
    0.39
    ୟ
    0.39
    の意味
    0.36
     frmt
    0.36
    daad
    0.36
    ഥ
    0.35
     datum
    0.35
    chaoxing
    0.35
    ︎
    0.35
     ಮಾ
    0.34
    POSITIVE LOGITS
     didn
    0.38
    گی
    0.38
    足
    0.38
    ونک
    0.37
    šla
    0.36
    გი
    0.36
     coz
    0.36
    ç
    0.35
     snaps
    0.35
    치
    0.35
    Activations Density 0.000%

    No Known Activations