© 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
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 129913
    Prev
    Next
    INDEX
    Explanations

    blood pressure cardiovascular health

    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_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
     don
    0.24
     मंगल
    0.24
     hizo
    0.24
     Did
    0.22
     এটিকে
    0.22
    隊
    0.21
     pareil
    0.21
     Mess
    0.21
     Would
    0.21
     جعل
    0.21
    POSITIVE LOGITS
    bym
    0.23
    lek
    0.22
    drawiam
    0.22
     ஜீய
    0.21
    meth
    0.21
    hotmail
    0.21
    stellung
    0.21
    apeut
    0.21
    ropo
    0.21
    砟
    0.21
    Activations Density 0.014%

    No Known Activations