© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14529
    Prev
    Next
    INDEX
    Explanations

    LaTeX math mode expressions, especially those involving symbols, subscripts, and superscripts

    oai_token-act-pair · gemini-2.0-flash

    underscores and curly brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    RenderAtEndOf
    -0.79
    titleMargin
    -0.69
    UrlResolution
    -0.69
    ThroughAttribute
    -0.60
    ContextHolder
    -0.59
    وانید
    -0.52
     isolada
    -0.52
    complexContent
    -0.52
    weighed
    -0.52
    ográficas
    -0.50
    POSITIVE LOGITS
     astore
    0.53
    rrggbb
    0.52
    azar
    0.52
     jScrollPane
    0.50
    GEBURTS
    0.48
     NSCoder
    0.48
    WithIdentifier
    0.48
    elernt
    0.48
     дописавши
    0.48
    
    0.45
    Activations Density 3.303%

    No Known Activations