© 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
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 48093
    Prev
    Next
    INDEX
    Explanations

    list of items or conditions

    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
    but
    0.51
    DP
    0.49
    circular
    0.49
    export
    0.48
    has
    0.48
    6
    0.47
    focus
    0.47
    made
    0.47
    ka
    0.46
    had
    0.46
    POSITIVE LOGITS
     вели
    0.57
     previewBuilder
    0.57
     суще
    0.50
    谀
    0.50
     закон
    0.50
     обнару
    0.49
    пли
    0.49
     completos
    0.49
     висо
    0.48
     necesit
    0.48
    Activations Density 0.000%

    No Known Activations