© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12686
    Prev
    Next
    INDEX
    Explanations

    Stephanie Holden

    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_13_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
     To
    0.55
    to
    0.54
    pers
    0.52
    V
    0.52
     family
    0.51
    ROW
    0.50
     Blacks
    0.48
     pers
    0.48
    POS
    0.47
     s
    0.47
    POSITIVE LOGITS
     desarrollo
    0.52
     entwick
    0.50
    -}$
    0.46
     الأه
    0.46
     utilizado
    0.46
     posibilidades
    0.46
    稱為
    0.45
     ADVISED
    0.45
    ạn
    0.45
    িয়োগ
    0.45
    Activations Density 0.000%

    No Known Activations