© 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. 229247
    Prev
    Next
    INDEX
    Explanations

    bartender downtime

    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
    nání
    0.42
    aceted
    0.41
     partitioned
    0.40
     faceted
    0.39
     ಬೆ
    0.38
    >),
    0.37
    xn
    0.37
    ate
    0.36
     Fluid
    0.36
    ⅙
    0.36
    POSITIVE LOGITS
    eder
    0.45
    役
    0.42
    ouche
    0.39
    pop
    0.38
    हाबाद
    0.38
     роль
    0.37
    BUUID
    0.37
    สัน
    0.37
    derm
    0.37
    edere
    0.37
    Activations Density 0.000%

    No Known Activations