© 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. 4240
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to international economics and finance

    oai_token-act-pair · gemini-2.0-flash

    mentions of foreign currency or the term 'hard'

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

    currency/foreign transactions

    np_max-act-logits · gemini-2.0-flash

    say "currency words"

    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_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
    ystick
    -0.57
     Cost
    -0.57
     contextLoads
    -0.57
     nickel
    -0.56
    UTELY
    -0.56
     Charge
    -0.55
     cost
    -0.54
     Ashland
    -0.54
     autorytatywna
    -0.53
    gée
    -0.53
    POSITIVE LOGITS
     hard
    0.89
    hard
    0.73
     harde
    0.71
    Hard
    0.68
     foreign
    0.68
     חיצוניים
    0.66
     Hard
    0.63
    HARD
    0.62
     HARD
    0.58
    foreign
    0.56
    Activations Density 0.895%

    No Known Activations