© 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. 12291
    Prev
    Next
    INDEX
    Explanations

    abdominal pain or urination

    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
    Geo
    0.39
    朔
    0.38
    trailing
    0.37
     Bo
    0.37
     Nab
    0.36
     लिं
    0.36
    遨
    0.35
    トム
    0.35
    ্যা
    0.35
    osim
    0.35
    POSITIVE LOGITS
     impl
    0.39
    യ
    0.39
     prescription
    0.37
    ırmaya
    0.37
    idE
    0.36
    Ө
    0.35
     Tetr
    0.35
     doughnut
    0.35
    ຟ
    0.35
     Quattro
    0.34
    Activations Density 0.042%

    No Known Activations