© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15905
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to pulmonology.

    oai_token-act-pair · gemini-2.0-flash

    lungs and 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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Lung
    -1.20
     lung
    -1.18
    Lung
    -1.06
     Chest
    -0.97
     pulmonary
    -0.95
     lungs
    -0.95
     chest
    -0.91
     Bron
    -0.88
     Pulmonary
    -0.88
     pulmonar
    -0.85
    POSITIVE LOGITS
     armed
    0.71
     surrounded
    0.67
     acompañado
    0.65
     rodeado
    0.65
     accompanied
    0.62
    Covered
    0.60
    Armed
    0.59
     entour
    0.58
     accompagné
    0.56
    accompanied
    0.56
    Activations Density 1.782%

    No Known Activations