© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18576
    Prev
    Next
    INDEX
    Explanations

    Berkeley Oakland locations

    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_40_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
     begs
    0.43
    ={{
    0.41
    aggable
    0.40
    [{{
    0.39
    িয়ার
    0.38
    ισμού
    0.38
     asymmetries
    0.38
     आगरा
    0.37
    ="{{
    0.36
     los
    0.36
    POSITIVE LOGITS
    Berkeley
    0.96
     Berkeley
    0.95
    berkeley
    0.69
     berk
    0.60
     Oakland
    0.59
     Berk
    0.57
    Berk
    0.55
     Alameda
    0.47
     BER
    0.46
    柏
    0.44
    Activations Density 0.019%

    No Known Activations