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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 14990
    Prev
    Next
    INDEX
    Explanations

    numeric dollar amounts and dates in financial documents

    oai_token-act-pair · gemini-2.0-flash

    numbers

    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
    üyada
    -0.73
     يتيمه
    -0.69
     AssemblyCulture
    -0.63
    يكب
    -0.58
     SIMBAD
    -0.57
    Biblia
    -0.57
    OpenHelper
    -0.56
    :][
    -0.55
    meanor
    -0.54
    ウンテン
    -0.54
    POSITIVE LOGITS
     ſeveral
    0.52
     Majefty
    0.52
    CodedInputStream
    0.51
    DispatchToProps
    0.51
     Twenty
    0.50
    ộng
    0.50
    Twenty
    0.49
     Theſe
    0.49
     Conſ
    0.49
     Thirty
    0.49
    Activations Density 6.313%

    No Known Activations