© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13913
    Prev
    Next
    INDEX
    Explanations

    language related to economic news and financial reports

    oai_token-act-pair · gemini-2.0-flash

    economic and market 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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     CWE
    -0.55
    /*
    -0.46
    бие
    -0.43
    RegressionTest
    -0.41
    uarga
    -0.41
    ствии
    -0.41
    Diese
    -0.40
    sø
    -0.40
    “”
    -0.40
    ú
    -0.40
    POSITIVE LOGITS
    styleType
    0.75
    UnsafeEnabled
    0.68
     SqlDbType
    0.68
     labour
    0.66
     Suez
    0.64
     Westmoreland
    0.64
     propOrder
    0.62
     Huguen
    0.62
     resign
    0.61
    Gweler
    0.61
    Activations Density 3.864%

    No Known Activations