© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6451
    Prev
    Next
    INDEX
    Explanations

    words related to policy changes and certifications in healthcare

    oai_token-act-pair · gemini-2.0-flash

    professional qualifications/accreditation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Вікіпе
    -0.67
    MemoryWarning
    -0.54
     chi̍t
    -0.53
    ajuku
    -0.53
    tangentMode
    -0.52
    يمق
    -0.51
    funds
    -0.50
    findpost
    -0.49
    ритори
    -0.47
     Inspiration
    -0.47
    POSITIVE LOGITS
    stateProvider
    0.61
     RoutedEventArgs
    0.60
    ابراین
    0.57
    elerik
    0.53
     NSCoder
    0.50
    ViewChild
    0.50
    Hentet
    0.50
     PackageManager
    0.48
    celain
    0.48
     continuance
    0.48
    Activations Density 2.565%

    No Known Activations