© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2525
    Prev
    Next
    INDEX
    Explanations

    LaTeX math delimiters and other math symbols.

    oai_token-act-pair · gemini-2.0-flash

    mathematical formulas

    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
    <bos>
    -0.52
    SharedCtor
    -0.48
    open
    -0.47
    ice
    -0.44
    ↵↵
    -0.43
    Na
    -0.43
     faudra
    -0.42
     open
    -0.42
    ari
    -0.42
     fallait
    -0.42
    POSITIVE LOGITS
    ScopeManager
    0.97
    IntoConstraints
    0.90
    TagHelper
    0.84
     AssemblyCompany
    0.82
     Audiodateien
    0.77
    setVerticalGroup
    0.77
     EconPapers
    0.73
    extAlignment
    0.69
    Filmographie
    0.68
     समीक्षक
    0.68
    Activations Density 1.972%

    No Known Activations