© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 222095
    Prev
    Next
    INDEX
    Explanations

    Chinese accent marks or characters

    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_10_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
    s
    1.02
    ;
    0.93
    я
    0.91
    ،
    0.91
    .
    0.88
    4
    0.86
    ی
    0.86
    ק
    0.85
    ных
    0.84
    -
    0.82
    POSITIVE LOGITS
    pentine
    0.73
    폿
    0.72
    粎
    0.72
    osion
    0.71
     Abhishek
    0.68
    ቀም
    0.66
    ledad
    0.66
    ફેદ
    0.66
     Сасик
    0.66
     þei
    0.66
    Activations Density 0.000%

    No Known Activations