© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14690
    Prev
    Next
    INDEX
    Explanations

    code snippets that contain characters used for formatting, punctuation, and certain keywords, especially related to XML and JSON parsing

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    <h2>
    -0.42
    <em>
    -0.39
    .
    -0.36
      
    -0.35
    
    -0.35
    тельством
    -0.35
    <h3>
    -0.35
    Stre
    -0.34
    ментом
    -0.34
     द्वारा
    -0.33
    POSITIVE LOGITS
    enumi
    0.74
    elemField
    0.73
    TagMode
    0.73
    RenderAtEndOf
    0.72
     оригіналу
    0.71
    ciclop
    0.71
     typelib
    0.70
    出版年
    0.70
    AutoField
    0.68
    CodeAttribute
    0.68
    Activations Density 1.544%

    No Known Activations