© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10412
    Prev
    Next
    INDEX
    Explanations

    vocabulary related to the stock market, percentages, inflation, and CPI (Consumer Price Index).

    oai_token-act-pair · gemini-2.0-flash

    Y

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    NOPQRST
    -0.63
     متعلقه
    -0.57
     ambientale
    -0.55
    енча
    -0.54
    esterno
    -0.54
    Filling
    -0.53
    циони
    -0.52
    ganu
    -0.52
     modellen
    -0.51
    ientí
    -0.51
    POSITIVE LOGITS
     względem
    0.54
     Comparing
    0.53
     gegenüber
    0.52
     comparing
    0.52
     compar
    0.52
     comparative
    0.51
    Comparing
    0.50
    TagMode
    0.49
    Демографія
    0.47
     comparison
    0.46
    Activations Density 1.581%

    No Known Activations