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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11273
    Prev
    Next
    INDEX
    Explanations

    regular expressions that define URL-related patterns

    oai_token-act-pair · gemini-2.0-flash

    non-English or programming terms

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

    Code/regex related

    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
    WebVitals
    -0.72
    DockStyle
    -0.71
     سكانية
    -0.65
    ScopeManager
    -0.63
    ^(@)
    -0.63
     propTypes
    -0.59
     EconPapers
    -0.59
     
    -0.57
     ویکی‌آمباردا
    -0.57
    ())))
    -0.57
    POSITIVE LOGITS
    تقاوى
    0.65
    脚注の使い方
    0.61
    AndroidJUnit
    0.58
    webElementGuid
    0.53
    ppard
    0.52
    #[
    0.49
    DataAnnotations
    0.48
    +[
    0.48
    ואר
    0.47
    etry
    0.46
    Activations Density 4.496%

    No Known Activations