© 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. 7649
    Prev
    Next
    INDEX
    Explanations

    `if __name__ == "__main__":`

    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
    a
    2.02
    it
    1.80
    ar
    1.79
    ا
    1.74
    দের
    1.71
    ensory
    1.69
    ol
    1.69
    ા
    1.66
    ה
    1.66
    🏼
    1.66
    POSITIVE LOGITS
    𝗡
    1.81
    EN
    1.80
    𝗻
    1.80
     prej
    1.70
    CH
    1.67
    館
    1.65
    𝗜
    1.61
    ну
    1.61
    NC
    1.57
    𝑔
    1.57
    Activations Density 0.033%

    No Known Activations