© 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
    2. Gemma-3-27B-IT
    3. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 165272
    Prev
    Next
    INDEX
    Explanations

    extracts and navigation

    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
    និង
    0.56
     ء
    0.50
    Ả
    0.47
    jom
    0.46
     Aś
    0.45
     文章
    0.45
     squadrons
    0.45
     Aircraft
    0.45
     形
    0.44
     Baat
    0.44
    POSITIVE LOGITS
    ielle
    0.46
     texas
    0.44
     runner
    0.44
     Runner
    0.43
    場合に
    0.43
     colle
    0.43
    各国
    0.42
     دوسروں
    0.42
    縁
    0.42
    깐
    0.41
    Activations Density 0.000%

    No Known Activations