© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34688
    Prev
    Next
    INDEX
    Explanations

    power switch or control exchange

    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_3_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
    1
    0.72
    3
    0.70
    t
    0.68
    ir
    0.65
    in
    0.64
    the
    0.63
     في
    0.63
    ução
    0.62
    (
    0.62
     مرة
    0.60
    POSITIVE LOGITS
    C
    0.82
    A
    0.70
    P
    0.70
    व
    0.68
    داری
    0.65
    I
    0.65
    D
    0.65
    M
    0.63
    ﾝ
    0.63
    ﾑ
    0.62
    Activations Density 0.009%

    No Known Activations