© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4057
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to pulmonary disease or infection

    oai_token-act-pair · gemini-2.0-flash

    medical terms related to respiratory conditions

    np_token-act-pair-logits · gpt-4o-mini

    Medical symptoms/observations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    mybatisplus
    -0.94
    BagConstraints
    -0.79
    存于互联网档案馆
    -0.78
    abetes
    -0.77
     Савезне
    -0.75
    amaño
    -0.74
     समीक्षाएं
    -0.74
    tvguidetime
    -0.73
    ViewImports
    -0.70
    uxxxx
    -0.70
    POSITIVE LOGITS
    선
    0.42
    にかけて
    0.42
    épisode
    0.42
     in
    0.41
    的精神
    0.40
     Cool
    0.39
    틴
    0.39
    pageTitle
    0.39
     photo
    0.39
    тан
    0.39
    Activations Density 1.711%

    No Known Activations