© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5424
    Prev
    Next
    INDEX
    Explanations

    javascript code related to rendering and state management in a React component, specifically focusing on loading indicators, conditional rendering based on data availability, and list presentation using FlatList.

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     component
    -1.00
     componente
    -0.87
     Component
    -0.86
    component
    -0.85
     components
    -0.84
     COMPONENT
    -0.81
     Components
    -0.79
    Props
    -0.78
    Component
    -0.75
    components
    -0.74
    POSITIVE LOGITS
    rrggbb
    0.67
    Autoritní
    0.63
     Wikimédia
    0.51
    iritto
    0.49
     viewDidLoad
    0.48
    addPreferredGap
    0.47
    jface
    0.47
     Vía
    0.46
     doInBackground
    0.46
     استنادى
    0.46
    Activations Density 0.197%

    No Known Activations