© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13489
    Prev
    Next
    INDEX
    Explanations

    financial jargon related to markets, funds, and risk

    oai_token-act-pair · gemini-2.0-flash

    finance and markets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    <bos>
    -0.88
    TagHelper
    -0.49
    itarios
    -0.44
    ValueStyle
    -0.42
     dados
    -0.38
    αι
    -0.37
    oredCriteria
    -0.37
     fly
    -0.37
     Per
    -0.36
    fly
    -0.35
    POSITIVE LOGITS
    таратура
    0.71
     saites
    0.70
    addContainerGap
    0.70
     OMITBAD
    0.69
    Disliked
    0.69
    EntityFramework
    0.69
    AsUp
    0.67
    tableFuture
    0.67
    IndentedString
    0.66
    tonsoft
    0.65
    Activations Density 1.143%

    No Known Activations