© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7863
    Prev
    Next
    INDEX
    Explanations

    mathematical/code symbols and formulas

    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
    ::::::
    3.88
    ت
    3.69
    ה
    3.44
    犸
    3.29
    сибо
    2.99
    ::::
    2.95
    মূল
    2.95
    𝐢
    2.81
    />}
    2.81
    ης
    2.76
    POSITIVE LOGITS
    ي
    3.95
    ু
    3.17
     якія
    2.94
    ский
    2.90
     underestimate
    2.84
     faptul
    2.84
     الغذ
    2.73
     overwhelm
    2.71
     хоть
    2.68
    ar
    2.66
    Activations Density 0.218%

    No Known Activations