© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42525
    Prev
    Next
    INDEX
    Explanations

    format with parentheses or percentage

    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_22_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
     เหมือน
    0.11
    เหมือน
    0.10
     moor
    0.10
    ooli
    0.10
     Pawan
    0.10
    ObjectModel
    0.10
    🏗
    0.10
     profits
    0.10
     Shabd
    0.10
     Profits
    0.10
    POSITIVE LOGITS
    or
    0.12
     குறிப்பிட்ட
    0.11
    區
    0.11
     THEY
    0.11
    commun
    0.11
     selected
    0.10
     DON
    0.10
    correlated
    0.10
    区
    0.10
     estimated
    0.10
    Activations Density 0.008%

    No Known Activations