© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210375
    Prev
    Next
    INDEX
    Explanations

    medical procedures and terminology

    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_20_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
     alleviated
    0.29
     alleviate
    0.28
     सर्टिफिकेट
    0.27
     Scare
    0.27
     ઓછા
    0.27
     sogenannten
    0.27
     améliorer
    0.26
    ;//
    0.25
    ();//
    0.25
    ();
    0.25
    POSITIVE LOGITS
     testifying
    0.27
     periphery
    0.26
     decoupled
    0.26
     vacuo
    0.25
    ரியா
    0.25
    บค้น
    0.25
    QRect
    0.25
    api
    0.25
     cumpr
    0.24
     testify
    0.24
    Activations Density 0.001%

    No Known Activations