© 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. 12027
    Prev
    Next
    INDEX
    Explanations

    parts of C++ code, specifically template declarations and function definitions including parentheses and types.

    oai_token-act-pair · gemini-2.0-flash

    parentheses/greater-than signs

    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
    存于互联网档案馆
    -0.59
     RoutedEventArgs
    -0.54
    avits
    -0.52
     onOptions
    -0.51
    EDES
    -0.50
     Pristupljeno
    -0.50
    ="'+
    -0.50
    IMATE
    -0.49
    ,:)
    -0.48
    InputBorder
    -0.47
    POSITIVE LOGITS
    ConstraintMaker
    0.70
    reportWebVitals
    0.68
     automatiques
    0.56
    CreateModel
    0.54
    WithIOException
    0.52
    findpost
    0.50
    oa̍t
    0.49
    RunAsync
    0.48
     EconPapers
    0.47
    EndInit
    0.47
    Activations Density 0.977%

    No Known Activations