© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 15502
    Prev
    Next
    INDEX
    Explanations

    README.md

    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_40_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
     夕
    0.30
     stereotypes
    0.28
    體
    0.28
     incarcer
    0.28
    neze
    0.28
    <0xAA>
    0.27
     চাপে
    0.27
    け
    0.27
    厂
    0.27
     terg
    0.27
    POSITIVE LOGITS
    Domain
    0.35
    Virt
    0.33
    EventHandler
    0.33
    Equivalent
    0.33
     Equival
    0.32
     Equivalent
    0.32
    Extensions
    0.32
    gry
    0.31
    Egg
    0.31
     Oxford
    0.31
    Activations Density 0.002%

    No Known Activations