© 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-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4123
    Prev
    Next
    INDEX
    Explanations

    terminology related to medical procedures, especially anesthesia and infusions

    oai_token-act-pair · gemini-2.0-flash

    medical procedures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ComVisible
    -0.66
     contextLoads
    -0.66
    TagMode
    -0.57
    šanai
    -0.57
    AutoScaleMode
    -0.56
     Kompon
    -0.55
    Sucesor
    -0.55
     consultato
    -0.55
    ostatic
    -0.55
    новниш
    -0.54
    POSITIVE LOGITS
     AssemblyTitle
    0.62
    RUnlock
    0.48
    featureID
    0.48
     CURIAM
    0.46
     potenti
    0.43
    ObjectMeta
    0.43
     EconPapers
    0.42
    enziale
    0.42
    lanc
    0.41
    ivant
    0.41
    Activations Density 2.488%

    No Known Activations