© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40188
    Prev
    Next
    INDEX
    Explanations

    sissy

    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_11_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
    ન
    0.73
    न
    0.64
     to
    0.63
     =
    0.62
    ку
    0.61
     on
    0.59
    گ
    0.58
    ア
    0.58
    は
    0.57
    о
    0.57
    POSITIVE LOGITS
     επίσης
    0.61
     ايضا
    0.57
    ederal
    0.57
     década
    0.57
     များ
    0.54
    amientos
    0.54
     মিত্র
    0.52
     irão
    0.52
    omnia
    0.52
    rifle
    0.52
    Activations Density 0.011%

    No Known Activations