© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15528
    Prev
    Next
    INDEX
    Explanations

    references to U.S. patent applications and patents

    oai_token-act-pair · gemini-2.0-flash

    US patents

    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
     pat
    -1.01
     patent
    -0.96
     patents
    -0.92
     Intellectual
    -0.88
     Patent
    -0.88
    pat
    -0.86
     trade
    -0.86
     intellectual
    -0.85
     IP
    -0.85
     Pat
    -0.83
    POSITIVE LOGITS
     Roskov
    0.68
    InSection
    0.67
    queryInterface
    0.65
     ErrIntOverflow
    0.57
    UNUSED
    0.55
    
    0.52
     compléter
    0.51
     mej
    0.50
    блица
    0.50
    श्चित
    0.50
    Activations Density 0.783%

    No Known Activations