© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11341
    Prev
    Next
    INDEX
    Explanations

    mentions of currency or the act of paying for things

    oai_token-act-pair · gemini-2.0-flash

    Currency symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     thousands
    -1.00
     Thousands
    -0.86
    thousands
    -0.84
     thousand
    -0.84
    Thousands
    -0.81
    InjectAttribute
    -0.76
     Majefty
    -0.73
     тысячи
    -0.73
     chofe
    -0.69
    thâu
    -0.69
    POSITIVE LOGITS
    eland
    0.54
     nakalista
    0.47
    amb
    0.47
     execução
    0.45
    泣き
    0.44
     cuarenta
    0.44
    CHN
    0.43
    ew
    0.43
    DataBind
    0.43
    дри
    0.42
    Activations Density 0.611%

    No Known Activations