© 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. 46502
    Prev
    Next
    INDEX
    Explanations

    for

    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
    w
    0.43
    in
    0.42
    ا
    0.41
    oq
    0.40
    p
    0.37
    location
    0.36
    on
    0.35
    o
    0.35
    slot
    0.35
    ол
    0.34
    POSITIVE LOGITS
    istä
    0.35
     tror
    0.35
     musik
    0.35
     naan
    0.35
     bija
    0.34
    ,",
    0.34
     leto
    0.34
     kah
    0.33
     drugih
    0.33
     není
    0.33
    Activations Density 0.027%

    No Known Activations