© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3014
    Prev
    Next
    INDEX
    Explanations

    DLL, network, Logon, Startup

    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_39_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
    賦
    0.30
    ENTITY
    0.29
     ক্লে
    0.29
    fry
    0.29
    メール
    0.29
    لنا
    0.29
     nodemailer
    0.28
    輪
    0.28
    窓
    0.28
    urch
    0.28
    POSITIVE LOGITS
     DLL
    0.35
    dll
    0.34
     Logon
    0.34
    Startup
    0.33
     Startup
    0.33
     PBL
    0.32
     ATL
    0.32
     Aging
    0.31
     logon
    0.31
    BES
    0.31
    Activations Density 0.080%

    No Known Activations