Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14727
    Prev
    Next
    INDEX
    Explanations

    code snippets in C# .NET

    oai_token-act-pair · gemini-2.0-flash

    computer 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
    IonicModule
    -0.68
    DataAnnotations
    -0.63
     dAtA
    -0.62
    __':
    
    -0.59
     verla
    -0.59
    ]=>
    -0.59
    __":
    
    -0.57
    prepareStatement
    -0.56
    Fns
    -0.55
    DoubleQuotes
    -0.54
    POSITIVE LOGITS
     resourceCulture
    0.52
    setCellValue
    0.52
     Hand
    0.52
    InsertCommand
    0.48
     Field
    0.48
    Field
    0.48
    Hand
    0.45
    gul
    0.45
    swatch
    0.44
     Einwilligung
    0.44
    Activations Density 0.620%

    No Known Activations