© 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. 4353
    Prev
    Next
    INDEX
    Explanations

    references to dollar amounts

    oai_token-act-pair · gemini-2.0-flash

    large sums of money

    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
     hundred
    -0.76
     hundreds
    -0.76
     Hundreds
    -0.73
     HUND
    -0.69
    Hundreds
    -0.65
    hundreds
    -0.65
    ArrowToggle
    -0.64
    BagLayout
    -0.64
     Hundred
    -0.63
    <>());
    -0.63
    POSITIVE LOGITS
    NOPQRST
    0.52
    createServer
    0.50
     ten
    0.47
    ďaka
    0.46
    níků
    0.44
    Ten
    0.44
    bledon
    0.43
    пой
    0.43
     remercie
    0.43
     Ten
    0.42
    Activations Density 0.799%

    No Known Activations