© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6677
    Prev
    Next
    INDEX
    Explanations

    code-related terms and questions, especially terms like "API", snippets of logic and question words

    oai_token-act-pair · gemini-2.0-flash

    programming and software

    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
    ⓘ
    -0.79
    DoubleQuotes
    -0.75
    Revenir
    -0.67
     ویکی‌پدیای
    -0.67
    Hochspringen
    -0.66
    تقاوى
    -0.65
    CppCodeGen
    -0.65
    AutoScaleMode
    -0.65
    invokeLater
    -0.64
    LLocation
    -0.64
    POSITIVE LOGITS
    ItemBackground
    0.47
    mployment
    0.43
     deal
    0.43
     work
    0.41
    etsk
    0.41
    paksa
    0.40
     technically
    0.40
    naeus
    0.40
     handle
    0.40
     달
    0.39
    Activations Density 2.245%

    No Known Activations