© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 197027
    Prev
    Next
    INDEX
    Explanations

    file copying and destination management

    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_26_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
     partea
    0.39
     ഒരു
    0.38
     Farewell
    0.37
     formidable
    0.37
    हू
    0.37
     毛
    0.37
     filamentous
    0.37
     מי
    0.37
    avalt
    0.37
     Is
    0.36
    POSITIVE LOGITS
     managed
    0.40
    爣
    0.38
     MPR
    0.38
     pred
    0.38
     sogen
    0.36
    ల్య
    0.36
    పథ
    0.35
     LMP
    0.35
     ট্যা
    0.35
     Managed
    0.35
    Activations Density 0.002%

    No Known Activations