© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80547
    Prev
    Next
    INDEX
    Explanations

    zig, windshield wipers

    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_0_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
    r
    1.98
    ন
    1.84
    ज
    1.67
    न
    1.63
    ম
    1.57
    ar
    1.55
    t
    1.55
    IS
    1.53
    어로
    1.53
    ل
    1.51
    POSITIVE LOGITS
     in
    2.00
     في
    1.54
    在
    1.38
    ية
    1.32
    ও
    1.23
    0
    1.22
    ני
    1.19
    も
    1.17
    もら
    1.16
    ﺩ
    1.13
    Activations Density 0.000%

    No Known Activations