© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12923
    Prev
    Next
    INDEX
    Explanations

    terms related to finance and markets including currencies, bonds, and interest rates

    oai_token-act-pair · gemini-2.0-flash

    tokens starting with '▁'

    np_token-act-pair-logits · gpt-4o-mini

    economics and finance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     feroit
    -0.99
     étoient
    -0.97
    ſelves
    -0.94
     myſelf
    -0.94
     avoient
    -0.94
     ainfi
    -0.93
     purpoſe
    -0.92
     ſtate
    -0.91
     itſelf
    -0.91
     reaſon
    -0.91
    POSITIVE LOGITS
    fromnode
    0.54
     cho
    0.54
     end
    0.51
     test
    0.50
     P
    0.50
    jes
    0.49
     trade
    0.49
     g
    0.48
     par
    0.48
    cho
    0.48
    Activations Density 0.863%

    No Known Activations