© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1769
    Prev
    Next
    INDEX
    Explanations

    C/C++ code blocks, specifically preprocessor directives like #if, #else, #endif, #define, and #pragma.

    oai_token-act-pair · gemini-2.0-flash

    #

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    "
    -0.52
     st
    -0.47
     cu
    -0.46
     l
    -0.45
    rictions
    -0.42
     laid
    -0.41
    Activité
    -0.41
    Activités
    -0.41
    モト
    -0.40
    ERATION
    -0.40
    POSITIVE LOGITS
    ViewImports
    0.82
    webElementXpaths
    0.82
    AccessorTable
    0.79
     typelib
    0.73
     resourceCulture
    0.72
    ArrowToggle
    0.72
     disambiguazione
    0.72
     betweenstory
    0.72
    انجليز
    0.70
     étanche
    0.68
    Activations Density 6.859%

    No Known Activations