© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144651
    Prev
    Next
    INDEX
    Explanations

    brig or CR followed by critical/lig/ado/ade

    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
    ส์
    1.48
    తో
    1.39
    $).
    1.28
    $
    1.28
    트를
    1.24
    ;
    1.24
     as
    1.20
    드
    1.17
    )!
    1.16
    ジタル
    1.16
    POSITIVE LOGITS
    am
    2.03
    om
    1.89
    4
    1.84
    im
    1.80
    os
    1.79
    al
    1.71
    2
    1.70
    s
    1.68
    ad
    1.67
    ak
    1.62
    Activations Density 0.000%

    No Known Activations