© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261394
    Prev
    Next
    INDEX
    Explanations

    Don Shirley Ali jazz pianist

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_5_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
    مان
    1.28
    ல்
    1.23
    1.20
    مة
    1.15
    t
    1.13
    ong
    1.13
    ાર
    1.12
    áról
    1.07
    watcher
    1.04
    ਰ
    1.02
    POSITIVE LOGITS
    s
    1.41
     at
    1.33
    1
    1.31
    5
    1.31
    ה
    1.30
    ی
    1.27
    ב
    1.26
    ح
    1.23
     up
    1.22
    ;
    1.13
    Activations Density 0.000%

    No Known Activations