© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132432
    Prev
    Next
    INDEX
    Explanations

    the vast majority of

    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_6_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
    0.94
    ون
    0.93
    ك
    0.89
    는
    0.87
    은
    0.86
    <0xAC>
    0.79
    들이
    0.79
    >
    0.77
    也
    0.77
     instinctive
    0.76
    POSITIVE LOGITS
    ak
    1.16
    on
    1.10
    ad
    1.08
    o
    1.08
    un
    1.04
    ok
    0.93
    as
    0.90
    ot
    0.89
    os
    0.89
    ai
    0.89
    Activations Density 0.001%

    No Known Activations