© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 27314
    Prev
    Next
    INDEX
    Explanations

    variable declarations or counts

    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
     calculators
    0.37
     calcula
    0.37
     возраст
    0.36
     nucl
    0.35
     і
    0.34
     calculadora
    0.34
     το
    0.33
     в
    0.33
    ﺭ
    0.33
     רא
    0.33
    POSITIVE LOGITS
    in
    0.43
    ani
    0.32
    مان
    0.31
    time
    0.28
    kk
    0.28
    onant
    0.27
    ímenes
    0.27
     Gutiérrez
    0.27
    né
    0.27
    s
    0.27
    Activations Density 0.189%

    No Known Activations