© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2161
    Prev
    Next
    INDEX
    Explanations

    mentions of money, assets, and finance

    oai_token-act-pair · gemini-2.0-flash

    dollar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     dollar
    -1.16
     Dollar
    -1.06
     dollars
    -1.05
    dollar
    -0.99
     Dollars
    -0.99
     percent
    -0.98
    Dollar
    -0.96
    dollars
    -0.87
     DOLLARS
    -0.85
    percent
    -0.84
    POSITIVE LOGITS
    weilen
    0.51
     useCallback
    0.50
    udy
    0.45
    Diweddarwch
    0.44
     tratti
    0.43
     riesgo
    0.43
     R
    0.42
    amqp
    0.42
     sibuk
    0.42
     consultas
    0.42
    Activations Density 12.969%

    No Known Activations