© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11607
    Prev
    Next
    INDEX
    Explanations

    C and C++ code snippets, especially preprocessor directives

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    NameInMap
    -0.57
    setVerticalGroup
    -0.54
     RIB
    -0.53
    ImageContext
    -0.49
     AssemblyCulture
    -0.45
    AndEndTag
    -0.44
    ."</
    -0.43
    onViewCreated
    -0.43
     *:
    -0.43
    Configurer
    -0.42
    POSITIVE LOGITS
    //#
    0.62
    #
    0.59
    /*@
    0.56
    netinet
    0.55
    öbb
    0.54
    EXPORT
    0.52
    ///**
    0.52
    //@
    0.52
     közé
    0.52
    <tbody>
    0.51
    Activations Density 6.218%

    No Known Activations