© 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. 165336
    Prev
    Next
    INDEX
    Explanations

    political theory, system, and movements

    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
    ংখ্যান
    0.51
     ಫಲ
    0.48
    اؤ
    0.47
    盱
    0.46
     radionuclide
    0.46
    এখন
    0.46
     Chí
    0.46
     américains
    0.46
     conifers
    0.45
    Ⲇ
    0.45
    POSITIVE LOGITS
    -
    0.70
     '
    0.56
    0.50
    vis
    0.49
    ll
    0.48
    ik
    0.48
     =
    0.47
    self
    0.46
    )
    0.46
    ated
    0.45
    Activations Density 0.068%

    No Known Activations