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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16296
    Prev
    Next
    INDEX
    Explanations

    code snippets with `std::` and template-heavy C++ code

    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/layer_20/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setupUi
    -0.63
     Telescope
    -0.50
    MatButtonModule
    -0.50
    £
    -0.46
     发表于
    -0.46
    anoma
    -0.44
    发表于
    -0.43
     succes
    -0.42
     entendimiento
    -0.42
     bVar
    -0.41
    POSITIVE LOGITS
    ſelf
    0.63
    ftagPool
    0.58
     calendriers
    0.58
     Shakspeare
    0.57
     itſelf
    0.57
    BibitemShut
    0.57
    bibinfo
    0.56
     CreateTagHelper
    0.55
    الدراسه
    0.54
    ErrorListener
    0.54
    Activations Density 1.315%

    No Known Activations