© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165318
    Prev
    Next
    INDEX
    Explanations

    workaround or solution

    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_13_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
    ﺸ
    0.31
     warehouse
    0.30
     manzana
    0.27
     जागरण
    0.26
    )</
    0.26
     czł
    0.26
    enzione
    0.25
     Página
    0.25
     westbound
    0.25
    ̳
    0.25
    POSITIVE LOGITS
    like
    0.34
    /
    0.33
    y
    0.30
    အစိတ်အပိုင်း
    0.29
    ing
    0.29
      
    0.29
    ési
    0.28
    ليب
    0.28
    #
    0.27
    gust
    0.27
    Activations Density 0.016%

    No Known Activations