© 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-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39661
    Prev
    Next
    INDEX
    Explanations

    Korean and Chinese characters, foreign syllables

    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_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
    in
    1.12
    ing
    0.93
     A
    0.93
    ;
    0.91
     I
    0.83
    的外
    0.82
     Ö
    0.80
    0.77
     E
    0.77
     Þ
    0.76
    POSITIVE LOGITS
    ни
    1.03
    ים
    0.93
    ের
    0.87
    dincer
    0.86
    ی
    0.86
    на
    0.85
    сний
    0.79
    ур
    0.76
    ्स
    0.76
    יות
    0.73
    Activations Density 0.000%

    No Known Activations