© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 32121
    Prev
    Next
    INDEX
    Explanations

    every

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    Electronic
    0.38
     않고
    0.37
     thành
    0.37
     Pseud
    0.37
    льном
    0.37
    [&
    0.37
     Vulcan
    0.37
     Pseudo
    0.37
    льному
    0.36
    льных
    0.36
    POSITIVE LOGITS
     every
    1.70
    every
    1.53
    Every
    1.38
     Every
    1.34
    每
    1.31
     ogni
    1.29
     setiap
    1.16
     كل
    1.15
    ทุก
    1.15
     हर
    1.07
    Activations Density 0.023%

    No Known Activations