© 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. 10767
    Prev
    Next
    INDEX
    Explanations

    words that are part of logical/mathematical arguments and/or are associated with fonts.

    oai_token-act-pair · 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
     الرياضيه
    -0.77
     EconPapers
    -0.75
     maș
    -0.68
     înal
    -0.67
     puteți
    -0.67
     Dumnezeu
    -0.67
     viață
    -0.67
     européennes
    -0.66
     financières
    -0.66
     ddelweddau
    -0.65
    POSITIVE LOGITS
     Mura
    0.73
     Guil
    0.67
     Coul
    0.67
     Pfe
    0.67
     Ral
    0.66
     Gera
    0.66
     Hoff
    0.65
     Bie
    0.65
     Bast
    0.65
     Kik
    0.65
    Activations Density 25.737%

    No Known Activations