© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 130714
    Prev
    Next
    INDEX
    Explanations

    ความรู้สึก/ความเหมาะสม

    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_25_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
     基于
    0.29
    endip
    0.27
    urals
    0.27
     请
    0.26
     poiché
    0.26
    工作的
    0.25
     adına
    0.25
    🕯
    0.25
     لانه
    0.25
    计算机
    0.25
    POSITIVE LOGITS
    स
    0.26
    تي
    0.26
    State
    0.26
     quy
    0.26
    वण्यासाठी
    0.26
     Sở
    0.26
    Emulator
    0.24
    ส
    0.24
     Nguyễn
    0.24
    ội
    0.24
    Activations Density 0.003%

    No Known Activations