© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13500
    Prev
    Next
    INDEX
    Explanations

    language related to patents and legal documents

    oai_token-act-pair · gemini-2.0-flash

    patents and inventions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    -2.03
     pat
    -2.02
     Pat
    -1.99
    Pat
    -1.90
    PAT
    -1.88
    pat
    -1.77
     Patent
    -1.59
     Patents
    -1.52
     patent
    -1.49
    Patent
    -1.47
    POSITIVE LOGITS
     OFDb
    0.56
     émissions
    0.51
     ägg
    0.51
     skolen
    0.47
     uova
    0.46
     religieuses
    0.45
     responsabilità
    0.45
     œufs
    0.45
     producteurs
    0.45
    المناصب
    0.44
    Activations Density 2.489%

    No Known Activations