© 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. 82535
    Prev
    Next
    INDEX
    Explanations

    magnum, magma, magical, magazines

    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
    是
    2.08
    的
    1.77
    ни
    1.70
    ش
    1.58
    is
    1.51
    on
    1.44
    ir
    1.42
    ز
    1.42
    র
    1.41
    是对
    1.36
    POSITIVE LOGITS
    ।
    1.68
    ။
    1.59
    ।'
    1.46
    。
    1.43
     ۷
    1.36
    $.
    1.34
    ۰
    1.34
    )।
    1.29
    ।’
    1.27
    。,
    1.26
    Activations Density 0.001%

    No Known Activations