© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13328
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to money, currency, and probability

    oai_token-act-pair · gemini-2.0-flash

    Currency/money/finance

    np_max-act-logits · gemini-2.0-flash

    say "money"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     coin
    -1.80
     currency
    -1.68
     Coin
    -1.62
     Currency
    -1.52
    Coin
    -1.50
     coins
    -1.48
    coin
    -1.43
     Coins
    -1.40
    Currency
    -1.40
    currency
    -1.38
    POSITIVE LOGITS
     Италијани
    0.63
    ArgumentParser
    0.60
    migrationBuilder
    0.57
    AndEndTag
    0.55
    ="@+
    0.55
    queryInterface
    0.53
     MainAxisSize
    0.52
     disambiguazione
    0.51
    ScopeManager
    0.50
    +#+#
    0.50
    Activations Density 0.746%

    No Known Activations