© 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. 46416
    Prev
    Next
    INDEX
    Explanations

    medical school

    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
     you
    0.40
     '')
    0.34
    inę
    0.31
     Computing
    0.30
    in
    0.30
    inį
    0.30
     る
    0.29
     pê
    0.29
    must
    0.29
     '?
    0.29
    POSITIVE LOGITS
    Здравствуйте
    0.40
    После
    0.36
     upregulated
    0.36
    Chào
    0.35
    {
    0.34
    Hallo
    0.33
    Merhaba
    0.33
    Привет
    0.33
    hle
    0.33
    Компания
    0.32
    Activations Density 0.002%

    No Known Activations