© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31363
    Prev
    Next
    INDEX
    Explanations

    medical testing equipment

    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_31_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
     biomarkers
    0.44
     sulfates
    0.40
    jahteraan
    0.39
    itol
    0.39
    untary
    0.37
    萜
    0.36
    ári
    0.36
     dimers
    0.36
     pharmacology
    0.35
     vár
    0.35
    POSITIVE LOGITS
    packaging
    0.40
     Bow
    0.39
     巻
    0.39
     Grad
    0.38
     பார்
    0.37
     Logger
    0.36
     Shun
    0.36
     புத்த
    0.36
     Vinci
    0.35
     Simplified
    0.35
    Activations Density 0.000%

    No Known Activations