© 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. 122312
    Prev
    Next
    INDEX
    Explanations

    Higarika School, dichotomy, Chediak-Higashi Syndrome

    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
    -
    0.73
    ral
    0.71
    ،
    0.70
     of
    0.70
    ii
    0.69
    itors
    0.67
     are
    0.62
    ।
    0.61
    $
    0.60
    。
    0.60
    POSITIVE LOGITS
    followlike
    0.70
     numa
    0.68
    ر
    0.63
     começ
    0.61
     başlad
    0.61
     счита
    0.58
     provoca
    0.58
    要做
    0.58
    トライ
    0.58
    SCAPE
    0.57
    Activations Density 0.000%

    No Known Activations