© 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. 12850
    Prev
    Next
    INDEX
    Explanations

    language related to economics

    oai_token-act-pair · gemini-2.0-flash

    terms related to economic metrics and trade

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

    Import/export demand

    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
     Италијани
    -0.77
     دیکھیے
    -0.77
    kapan
    -0.77
     Italijanski
    -0.72
     linkovi
    -0.71
     mergeFrom
    -0.69
     يتيمه
    -0.68
    المكان
    -0.68
    abestanden
    -0.68
    تقاوى
    -0.66
    POSITIVE LOGITS
     demand
    0.51
     import
    0.49
     consumption
    0.48
    qos
    0.43
     imports
    0.43
     importers
    0.42
     importing
    0.42
     volumes
    0.42
    Demand
    0.41
    AMPTON
    0.41
    Activations Density 0.637%

    No Known Activations