© 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. 31479
    Prev
    Next
    INDEX
    Explanations

    ---

    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
     ji
    0.38
     io
    0.38
     Ji
    0.37
    वाधिकार
    0.37
    料
    0.37
    --',
    0.36
     oyster
    0.36
     soul
    0.36
    गिरी
    0.36
    意见
    0.35
    POSITIVE LOGITS
     Maki
    0.35
    ؛
    0.35
     inasmuch
    0.35
    hydes
    0.33
    ˒
    0.33
    Carlo
    0.33
    َى
    0.32
    ký
    0.32
    ﺜ
    0.32
    ⠀⠀⠀⠀
    0.32
    Activations Density 0.012%

    No Known Activations