© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2252
    Prev
    Next
    INDEX
    Explanations

    a variety of code-related terms and citation information, including file paths, function calls (specifically "getField" variants), currency codes, and potentially author initials, indicating a focus on technical documentation or data within code.

    oai_token-act-pair · gemini-2.0-flash

    code and publications

    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
    Portale
    -0.63
    IBOutlet
    -0.49
     bouche
    -0.48
    ValueGenerated
    -0.48
     Worth
    -0.46
    agin
    -0.45
    otal
    -0.45
     lagi
    -0.44
    ([^
    -0.44
     pungkas
    -0.42
    POSITIVE LOGITS
    DoubleQuotes
    0.94
     autorytatywna
    0.80
     שוליים
    0.65
    TypedDataSet
    0.64
     Waray
    0.63
     propOrder
    0.61
     يتيمه
    0.60
    جغرافيا
    0.59
    DockStyle
    0.57
    Cyfeiriadau
    0.57
    Activations Density 0.356%

    No Known Activations