© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5079
    Prev
    Next
    INDEX
    Explanations

    lines of code or other strings of characters in a file

    oai_token-act-pair · gemini-2.0-flash

    programming terms or components

    np_token-act-pair-logits · gpt-4o-mini

    <

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    الإنجليزية
    -0.47
    isContained
    -0.43
     aş
    -0.42
    matchCondition
    -0.39
    saw
    -0.38
    sights
    -0.38
    Dougall
    -0.38
    HtmlAttribute
    -0.37
    ney
    -0.37
    ophore
    -0.36
    POSITIVE LOGITS
    ItemBackground
    0.81
     propOrder
    0.72
     MainAxisSize
    0.69
     समीक्षक
    0.67
    WebVitals
    0.62
    LookAnd
    0.62
    addContainerGap
    0.60
    WebpackPlugin
    0.59
    MLLoader
    0.59
    hastly
    0.58
    Activations Density 0.626%

    No Known Activations