© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79093
    Prev
    Next
    INDEX
    Explanations

    hai followed by Da or awk

    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
    s
    2.50
    k
    2.19
    de
    1.69
    Y
    1.68
    are
    1.66
    T
    1.56
    b
    1.55
    D
    1.53
    é
    1.52
    V
    1.52
    POSITIVE LOGITS
    ৫
    1.77
    り
    1.41
    し
    1.38
    ти
    1.27
     stave
    1.23
    ை
    1.19
    ী
    1.18
    ት
    1.17
    此同时
    1.14
    ని
    1.13
    Activations Density 0.000%

    No Known Activations