© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 108799
    Prev
    Next
    INDEX
    Explanations

    Japanese food items and names

    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_1_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
     on
    1.45
    on
    1.34
    .
    1.13
    in
    1.06
     from
    0.95
     diese
    0.95
    taro
    0.95
    ா
    0.93
    ת
    0.92
    عاد
    0.92
    POSITIVE LOGITS
    I
    1.57
    з
    1.56
     (
    1.54
    ;
    1.48
    ،
    1.41
    ",
    1.34
    A
    1.30
    O
    1.30
    :
    1.27
    ன்
    1.25
    Activations Density 0.000%

    No Known Activations