© 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. 12026
    Prev
    Next
    INDEX
    Explanations

    the words relating to economic transactions and organizations

    oai_token-act-pair · gemini-2.0-flash

    finance

    np_max-act · gemini-2.0-flash

    finance terms

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     autorytatywna
    -0.59
    IMPORTED
    -0.51
    ành
    -0.51
    getColumnIndex
    -0.50
     angry
    -0.48
     Reiz
    -0.47
    GeneratedMessage
    -0.47
    verton
    -0.47
    MediaStore
    -0.47
     hating
    -0.47
    POSITIVE LOGITS
    TagMode
    0.78
    OGND
    0.68
    KommentareTeilen
    0.66
    routeProvider
    0.61
     للاسماء
    0.59
    stateProvider
    0.59
    protoimpl
    0.58
     незавершена
    0.58
     salads
    0.56
    distan
    0.54
    Activations Density 0.580%

    No Known Activations