© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4161
    Prev
    Next
    INDEX
    Explanations

    language related to finance, especially concerning funds and money

    oai_token-act-pair · gemini-2.0-flash

    legal or financial context

    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
     financial
    -0.60
     monetary
    -0.54
     financière
    -0.54
     Catto
    -0.50
     money
    -0.45
    Money
    -0.44
    getAs
    -0.43
     financiero
    -0.43
     Money
    -0.43
     Monetary
    -0.43
    POSITIVE LOGITS
    MemoryWarning
    0.74
    +#+#
    0.73
    tvguidetime
    0.69
    WireFormatLite
    0.69
    PhysRev
    0.68
     kaarangay
    0.67
    extAlignment
    0.67
    +:+
    0.66
    queryInterface
    0.62
     defaultstate
    0.61
    Activations Density 2.405%

    No Known Activations