© 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. 211388
    Prev
    Next
    INDEX
    Explanations

    doctors who can prescribe

    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
     перемен
    0.32
     बंदर
    0.31
    矍
    0.31
     Elkus
    0.31
     机
    0.30
    ,*/}
    0.30
     पेर
    0.30
     положении
    0.30
    机的
    0.29
    宿
    0.29
    POSITIVE LOGITS
    Caf
    0.38
    Rec
    0.37
    skirts
    0.37
     গণহত্যা
    0.36
    ownicy
    0.36
     twentieth
    0.35
    Dance
    0.35
    wwww
    0.35
     hätten
    0.35
    AVC
    0.35
    Activations Density 0.003%

    No Known Activations