© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35426
    Prev
    Next
    INDEX
    Explanations

    U.S. Census Bureau estimates

    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
     mistura
    0.69
     ח
    0.68
     signific
    0.67
     operaciones
    0.67
     habían
    0.66
     fij
    0.64
     gable
    0.64
     měla
    0.63
    h
    0.63
     operações
    0.63
    POSITIVE LOGITS
    在
    0.71
    sky
    0.71
    서는
    0.70
    า
    0.69
    ని
    0.67
    ا
    0.64
    ้
    0.63
    ct
    0.63
    df
    0.63
    кто
    0.63
    Activations Density 0.000%

    No Known Activations