© 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. 15054
    Prev
    Next
    INDEX
    Explanations

    text related to finance, especially revenue, railroads, fines and costs.

    oai_token-act-pair · gemini-2.0-flash

    Finance, income, and revenue

    np_max-act-logits · gemini-2.0-flash
    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
     revenue
    -1.98
     income
    -1.96
     Income
    -1.90
     earnings
    -1.84
    Income
    -1.82
    Revenue
    -1.81
     Revenue
    -1.80
    revenue
    -1.80
     revenues
    -1.79
    income
    -1.70
    POSITIVE LOGITS
    .*")]
    0.55
    featureID
    0.48
     PRI
    0.47
     estekak
    0.47
    enderror
    0.46
    penup
    0.46
    localctx
    0.46
     spacer
    0.46
    Ψ
    0.45
    XmlAccessType
    0.44
    Activations Density 2.859%

    No Known Activations