© 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. 2075
    Prev
    Next
    INDEX
    Explanations

    phrases related to a wide range of specific industries

    oai_token-act-pair · gemini-2.0-flash

    terms related to sectors and industries

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

    sectors and industries

    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
     négociations
    -0.95
     spectateurs
    -0.91
     enfans
    -0.91
     touristes
    -0.91
     prisonniers
    -0.91
     bienfaits
    -0.91
     travailleurs
    -0.89
     bénévoles
    -0.87
     dieux
    -0.85
     bénéfices
    -0.85
    POSITIVE LOGITS
     regimes
    1.14
     departments
    1.04
     sectors
    1.04
     industries
    1.03
     environments
    1.02
     societies
    1.02
     budgets
    1.02
     periods
    1.01
     contexts
    0.97
     formats
    0.96
    Activations Density 5.230%

    No Known Activations