© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 9672
    Prev
    Next
    INDEX
    Explanations

    health

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
     medical
    0.84
    medical
    0.76
     veterinary
    0.69
    vang
    0.65
     health
    0.64
     value
    0.64
     MEDICAL
    0.64
    醫
    0.64
     মানবাধিকার
    0.63
    stattung
    0.63
    POSITIVE LOGITS
     consape
    0.78
     вопросы
    0.73
     eq
    0.72
     забо
    0.72
     સ્થ
    0.71
     cares
    0.70
    给我
    0.70
     situações
    0.70
    EQU
    0.69
    Lago
    0.69
    Activations Density 0.019%

    No Known Activations