© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7149
    Prev
    Next
    INDEX
    Explanations

    phrases containing "the" related to industries, economics, and infrastructure.

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "economy"

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

    economy

    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
     initComponents
    -0.75
     defaultstate
    -0.71
    Vidite
    -0.62
     estekak
    -0.62
     AssemblyProduct
    -0.61
    featureID
    -0.60
    CloseOperation
    -0.60
    AutoresizingMask
    -0.59
     uLocal
    -0.58
    InjectAttribute
    -0.58
    POSITIVE LOGITS
     economy
    1.57
    economy
    1.23
     Economy
    1.22
    Economy
    1.18
     ECONOMY
    1.14
     economies
    1.12
    économie
    1.05
     economia
    0.97
     economía
    0.93
     économie
    0.88
    Activations Density 1.487%

    No Known Activations