© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 314
    Prev
    Next
    INDEX
    Explanations

    scientific texts that contain numbers, temperatures, and measurements

    oai_token-act-pair · gemini-2.0-flash

    rate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     online
    -0.56
     G
    -0.49
     Online
    -0.46
     rowspan
    -0.46
     prefer
    -0.42
    UNTAS
    -0.41
     RoutedEventArgs
    -0.41
     system
    -0.40
    online
    -0.39
    オンライン
    -0.39
    POSITIVE LOGITS
    webElementXpaths
    0.80
     Juf
    0.71
    NameInMap
    0.69
     EconPapers
    0.69
     Meksiku
    0.68
    AccessorTable
    0.68
    +#+#
    0.67
    WriteBarrier
    0.66
    elemField
    0.65
    AddHtmlAttribute
    0.65
    Activations Density 1.762%

    No Known Activations