© 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
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 15268
    Prev
    Next
    INDEX
    Explanations

    snippets of code, specifically PHP and Javascript, and related keywords and symbols

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     this
    -2.66
    this
    -2.33
    This
    -1.85
     these
    -1.82
     This
    -1.78
     THIS
    -1.72
    these
    -1.63
    THIS
    -1.63
     questa
    -1.63
     dieses
    -1.56
    POSITIVE LOGITS
    
    0.85
    enderror
    0.79
    клопе
    0.75
    WebServlet
    0.70
    ngdoc
    0.64
    цездатний
    0.62
    Rüyada
    0.61
     समीक्षाओं
    0.60
    raszamy
    0.60
     noDo
    0.60
    Activations Density 0.806%

    No Known Activations