© 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. 171664
    Prev
    Next
    INDEX
    Explanations

    hypertension and high blood pressure

    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
     पूजन
    0.42
     aktiviert
    0.40
     использовать
    0.38
     inició
    0.38
    لوں
    0.38
     attiv
    0.37
    ﻴ
    0.37
    ほと
    0.37
    GOING
    0.36
    وجوان
    0.35
    POSITIVE LOGITS
     Bell
    0.38
    ędzy
    0.34
    rik
    0.33
     Neumann
    0.33
    rary
    0.33
    ometer
    0.33
    ബ്ര
    0.33
    script
    0.32
     Hour
    0.32
    ihad
    0.32
    Activations Density 0.002%

    No Known Activations