© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39666
    Prev
    Next
    INDEX
    Explanations

    "liao" or "le" followed by punctuation/particles

    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_11_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
    0.86
    Product
    0.83
    AND
    0.82
    Post
    0.78
    P
    0.78
    0.77
    1
    0.77
    Device
    0.77
     Stove
    0.73
    Page
    0.72
    POSITIVE LOGITS
     disagreed
    0.82
    ל
    0.80
    л
    0.73
    רי
    0.72
    на
    0.71
    ла
    0.71
    ﾝ
    0.70
    ть
    0.70
     denounced
    0.69
    ました
    0.67
    Activations Density 0.004%

    No Known Activations