© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5315
    Prev
    Next
    INDEX
    Explanations

    gravity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    ী
    0.73
    veel
    0.73
     ktor
    0.71
    즈
    0.69
    ৭
    0.69
    যার
    0.69
    ו
    0.68
     mám
    0.68
    şi
    0.68
    𝙙
    0.68
    POSITIVE LOGITS
    場合
    0.73
     Оста
    0.69
     Kindly
    0.62
     glancing
    0.62
    S
    0.61
     tablespoons
    0.61
    SScript
    0.61
     innate
    0.61
     gesamten
    0.60
     orthonormal
    0.60
    Activations Density 0.225%

    No Known Activations