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. 16153
    Prev
    Next
    INDEX
    Explanations

    code snippets containing networking terms and error handling involving "av", "dict", "set", and "transport."

    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
     Calling
    -0.45
    Calling
    -0.44
    sible
    -0.42
     calling
    -0.42
    Call
    -0.41
     φ
    -0.41
    lag
    -0.40
    OL
    -0.39
    ic
    -0.39
    Wondering
    -0.39
    POSITIVE LOGITS
     BrowserModule
    0.94
    reportWebVitals
    0.86
     Majefty
    0.85
     OnInit
    0.85
    queryInterface
    0.84
     Anſ
    0.82
    __":
    
    0.81
     pleaſure
    0.79
    ArgsConstructor
    0.77
    WriteLiteral
    0.77
    Activations Density 1.890%

    No Known Activations