© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8562
    Prev
    Next
    INDEX
    Explanations

    C++ code snippets using "->" and other keywords like "if," "void," and parameters, particularly those within game development contexts.

    oai_token-act-pair · gemini-2.0-flash

    detects 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_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    mybatisplus
    -0.81
     AssemblyCulture
    -0.69
    phosa
    -0.61
    tagHelperRunner
    -0.59
    MockMvc
    -0.59
    rrggbb
    -0.58
    lorum
    -0.57
     ويكيميديا
    -0.56
    HtmlAttribute
    -0.55
     getCity
    -0.55
    POSITIVE LOGITS
    IsInitialized
    0.57
     curious
    0.54
     shrug
    0.49
    IMPORTED
    0.46
    localize
    0.45
    flage
    0.45
     curiosity
    0.45
    ıyordu
    0.44
     shrugged
    0.44
     AssemblyCompany
    0.43
    Activations Density 0.373%

    No Known Activations