© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12829
    Prev
    Next
    INDEX
    Explanations

    words related to business, finance, and publicly traded companies

    oai_token-act-pair · gemini-2.0-flash

    technology companies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    kran
    -0.47
     rule
    -0.47
    踐
    -0.46
     trams
    -0.45
    MessageTagHelper
    -0.45
    TypedDataSet
    -0.43
    ycznej
    -0.43
     achat
    -0.43
     Regel
    -0.43
    throw
    -0.42
    POSITIVE LOGITS
    tvguidetime
    0.73
    currentColor
    0.70
    MLLoader
    0.68
    !("{
    0.68
    RegressionTest
    0.65
    новништво
    0.63
    aarrggbb
    0.63
    "])){
    0.63
    DoubleQuotes
    0.62
     Wikimédia
    0.61
    Activations Density 1.289%

    No Known Activations