© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1656
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to doctors and hospitals

    oai_token-act-pair · gemini-2.0-flash

    medical examination terms

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

    medical context

    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
    Negative Logits
    TagMode
    -1.02
    !*\
    -0.94
    ⓧ
    -0.86
    afficheront
    -0.77
     Himo
    -0.77
    lapsingToolbar
    -0.73
    AsUp
    -0.72
    帖最后由
    -0.69
    bootstrapcdn
    -0.68
    IntOverflow
    -0.68
    POSITIVE LOGITS
    Schedulers
    0.52
     r
    0.51
     diagnosed
    0.47
     λα
    0.44
    ärs
    0.42
     jä
    0.41
     diagnose
    0.40
    dited
    0.40
     ruling
    0.40
     Les
    0.40
    Activations Density 3.031%

    No Known Activations