© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9456
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to hospital departments and medical teams

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     getOrder
    -0.57
     TAMBÉM
    -0.57
    Étymologie
    -0.56
    inema
    -0.55
    tvguidetime
    -0.53
    ]<<"
    -0.53
     DVR
    -0.52
    Rè
    -0.52
     Numerade
    -0.52
     swatches
    -0.52
    POSITIVE LOGITS
     sezione
    0.51
    saraba
    0.49
    jScrollPane
    0.48
     humaines
    0.47
     initComponents
    0.47
    SourceChecksum
    0.46
     GenerationType
    0.46
     anciens
    0.45
    greenrobot
    0.45
    FieldBuilder
    0.45
    Activations Density 0.771%

    No Known Activations