© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 222032
    Prev
    Next
    INDEX
    Explanations

    court decisions and proceedings

    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_10_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
    v
    0.71
    屑
    0.67
    ל
    0.63
    ى
    0.63
    )){
    0.62
     County
    0.62
    vature
    0.60
    al
    0.60
     τὰ
    0.60
     Pelt
    0.59
    POSITIVE LOGITS
    s
    0.67
    UND
    0.66
    یی
    0.63
    ﺭ
    0.62
    י
    0.60
     иметь
    0.59
     blueprints
    0.58
     proximity
    0.57
     MAC
    0.57
    si
    0.57
    Activations Density 0.001%

    No Known Activations