© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 51220
    Prev
    Next
    INDEX
    Explanations

    medical devices and tech products

    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_10_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
    Ys
    0.63
    Y
    0.62
     über
    0.61
     spate
    0.57
     zam
    0.57
    Vs
    0.56
     הר
    0.56
     Über
    0.55
     spoil
    0.55
     spo
    0.55
    POSITIVE LOGITS
    {
    0.68
    
    0.59
    д
    0.58
    лын
    0.57
    د
    0.57
     অন্তর্
    0.56
     Programming
    0.56
     পরিমান
    0.55
    ++;//
    0.55
    пада
    0.54
    Activations Density 0.035%

    No Known Activations