© 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. 229211
    Prev
    Next
    INDEX
    Explanations

    story or scene

    np_max-act-logits · gemini-2.5-flash-lite
    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
     G
    0.39
    G
    0.38
    몰
    0.38
    mT
    0.36
     prelimin
    0.36
     Г
    0.35
     পাকিস্তান
    0.35
    เขียน
    0.35
    )-$
    0.35
     JO
    0.34
    POSITIVE LOGITS
    ネート
    0.38
    brite
    0.38
    Slope
    0.37
     inversa
    0.37
     Bruck
    0.36
     Broch
    0.36
     Ease
    0.35
    ванне
    0.35
     giác
    0.35
     composto
    0.35
    Activations Density 0.010%

    No Known Activations