© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13067
    Prev
    Next
    INDEX
    Explanations

    mentions of government, economics and politics

    oai_token-act-pair · gemini-2.0-flash

    Economy 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_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
     economy
    -1.73
     Economy
    -1.64
    economy
    -1.54
     Economic
    -1.50
     economic
    -1.47
    Economy
    -1.45
    Economic
    -1.43
     economically
    -1.41
    economic
    -1.40
     ECONOMY
    -1.39
    POSITIVE LOGITS
     nakalista
    0.52
    Configurer
    0.52
    ConstraintMaker
    0.48
    GoogleApiClient
    0.44
    InputModule
    0.44
    laub
    0.41
     cyr
    0.41
    AsUp
    0.40
     zuk
    0.39
     fluctuate
    0.38
    Activations Density 1.516%

    No Known Activations