© 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. 5714
    Prev
    Next
    INDEX
    Explanations

    various characters and symbols associated with code, particularly Java and XML.

    oai_token-act-pair · gemini-2.0-flash

    specific programming syntax or code elements

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

    Code punctuation

    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
    setVerticalGroup
    -0.82
    
    -0.80
     ویکی‌پدیا
    -0.75
    awtextra
    -0.72
    omeness
    -0.69
    MethodManager
    -0.68
     layui
    -0.67
     iprot
    -0.67
    újo
    -0.63
     ujednoznacz
    -0.62
    POSITIVE LOGITS
    azu
    0.45
    quilo
    0.43
    begin
    0.40
    hof
    0.39
    そうで
    0.39
     enge
    0.39
    ¿
    0.39
    Pre
    0.39
    bliž
    0.38
    To
    0.38
    Activations Density 0.860%

    No Known Activations