© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13767
    Prev
    Next
    INDEX
    Explanations

    language related to the stock market

    oai_token-act-pair · gemini-2.0-flash

    financial news

    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
     market
    -0.99
     Market
    -0.98
    market
    -0.96
    Market
    -0.91
     MARKET
    -0.90
     Markets
    -0.80
     MARKETS
    -0.79
     mercado
    -0.78
     markets
    -0.75
    AddTagHelper
    -0.75
    POSITIVE LOGITS
     متعلقه
    0.50
    auso
    0.48
    Genius
    0.47
    Одно
    0.46
     Genius
    0.44
    ખ
    0.43
    Defs
    0.43
    [++
    0.43
     paran
    0.41
     whatsoever
    0.41
    Activations Density 5.597%

    No Known Activations