© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10127
    Prev
    Next
    INDEX
    Explanations

    words related to medical research and biology

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Wikimédia
    -0.59
    ISupport
    -0.59
     onCancelled
    -0.56
    אלי
    -0.47
    lean
    -0.44
     Sykes
    -0.44
    ollectionView
    -0.43
    online
    -0.43
     industri
    -0.42
     commiss
    -0.42
    POSITIVE LOGITS
     незавершена
    0.78
     pengaturan
    0.60
    webElementXpaths
    0.59
    asantry
    0.59
    impianto
    0.57
     intptr
    0.56
    SourceChecksum
    0.56
    بوابة
    0.56
    arini
    0.55
    DockStyle
    0.54
    Activations Density 40.985%

    No Known Activations