© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14433
    Prev
    Next
    INDEX
    Explanations

    code syntax: comma followed by parenthesis or function

    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
    หน่าย
    0.43
    ృష్ణ
    0.43
     характери
    0.42
    น์โหลด
    0.39
    ্নের
    0.39
    ്യത
    0.38
    唖
    0.38
    satunya
    0.37
    输入的
    0.36
    㚣
    0.36
    POSITIVE LOGITS
     elevation
    0.46
    elev
    0.41
     patria
    0.41
     Elevation
    0.40
     matric
    0.39
     sut
    0.38
     Report
    0.38
    iyim
    0.38
     cadet
    0.38
     feder
    0.37
    Activations Density 0.001%

    No Known Activations