© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13262
    Prev
    Next
    INDEX
    Explanations

    capitalized words related to software and files, especially code

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act · 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
    RegressionTest
    -0.73
    WebServlet
    -0.71
    webElementXpaths
    -0.71
    verifyException
    -0.63
    aarrggbb
    -0.63
     الحره
    -0.61
     Infórmanos
    -0.58
    IntoConstraints
    -0.58
     EconPapers
    -0.57
     StatefulWidget
    -0.57
    POSITIVE LOGITS
     مشين
    0.54
    espero
    0.50
     ostavi
    0.48
    æus
    0.48
    ARSE
    0.47
    
    0.47
    mergeFrom
    0.46
    üz
    0.45
    fvar
    0.45
    æa
    0.45
    Activations Density 2.299%

    No Known Activations