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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10603
    Prev
    Next
    INDEX
    Explanations

    mentions of clinical studies and patient information

    oai_token-act-pair · gemini-2.0-flash

    clinical

    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
    PropertyChanging
    -0.73
     незавершена
    -0.61
     صوتيه
    -0.60
     Heizung
    -0.59
     Infórmanos
    -0.59
     ciment
    -0.59
     käytet
    -0.56
     ciasc
    -0.56
     paesaggio
    -0.56
     Wikimédia
    -0.55
    POSITIVE LOGITS
     estekak
    0.66
     [*]
    0.53
    robat
    0.52
    strtotime
    0.52
    :✨
    0.52
    Hochspringen
    0.50
    
    0.48
    formik
    0.47
     ress
    0.47
    awtextra
    0.46
    Activations Density 1.566%

    No Known Activations