© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 232502
    Prev
    Next
    INDEX
    Explanations

    Think about hints

    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_32_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
    PhysicalDevice
    0.42
    }}}^{
    0.41
    bajo
    0.40
    زاده
    0.40
    IMPORT
    0.39
    ба
    0.37
    輸入
    0.36
    vag
    0.36
    defined
    0.36
    nton
    0.36
    POSITIVE LOGITS
     lijkt
    0.42
    <unused70>
    0.38
     deviate
    0.37
     dioxygen
    0.37
    牡
    0.37
     seems
    0.36
     annotations
    0.36
     Seminar
    0.34
     เหมือน
    0.34
     réalise
    0.34
    Activations Density 0.002%

    No Known Activations