© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15254
    Prev
    Next
    INDEX
    Explanations

    code-related tokens that include the words "Float", "Double", and "Fixed"

    oai_token-act-pair · gemini-2.0-flash

    Float/double 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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     protoimpl
    -0.84
     مرئيه
    -0.72
     contextLoads
    -0.71
    double
    -0.69
    CppMethod
    -0.67
    AccessorTable
    -0.66
    Double
    -0.65
     Doubles
    -0.65
    batore
    -0.65
     doubles
    -0.64
    POSITIVE LOGITS
     f
    0.42
    f
    0.42
    woff
    0.42
    --;
    0.42
     af
    0.38
    Dav
    0.38
    ฟ
    0.37
     Fr
    0.36
     considerados
    0.36
    GeneratedCode
    0.35
    Activations Density 1.973%

    No Known Activations