© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 65303
    Prev
    Next
    INDEX
    Explanations

    constructor definitions like `public Type(Type param)`

    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_41_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
    زام
    0.43
    >',
    0.43
     플레이
    0.40
    (/[
    0.40
     алфа
    0.38
     পাহ
    0.37
    ЕМ
    0.37
    uí
    0.37
    asctime
    0.37
    里斯
    0.36
    POSITIVE LOGITS
    sy
    0.40
     manly
    0.39
     ControllerBase
    0.39
     मुझसे
    0.39
    Sy
    0.39
     محم
    0.38
    thiop
    0.36
     君
    0.35
     Negoti
    0.34
     लौटने
    0.34
    Activations Density 0.000%

    No Known Activations