© 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. 34641
    Prev
    Next
    INDEX
    Explanations

    fire hydrant escapes

    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
    ip
    0.84
    ater
    0.75
    rona
    0.68
    ０
    0.68
    𝙖
    0.68
    ai
    0.67
    ασ
    0.66
    す
    0.64
     a
    0.63
    نا
    0.62
    POSITIVE LOGITS
    ;
    0.90
    .
    0.76
     of
    0.73
    ри
    0.73
     fisica
    0.70
    -
    0.68
     ofthe
    0.67
    -(
    0.66
    .(
    0.66
    :
    0.66
    Activations Density 0.002%

    No Known Activations