© 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. 13559
    Prev
    Next
    INDEX
    Explanations

    mentions of patients, healthcare staff, and their relationship to the community

    oai_token-act-pair · gemini-2.0-flash

    patient

    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
    enumi
    -0.62
     MenuView
    -0.57
     themſelves
    -0.54
    seamnă
    -0.54
    ApiProperty
    -0.52
     cittadino
    -0.51
    ="#"><
    -0.50
     myſelf
    -0.50
    NameInMap
    -0.50
    endregion
    -0.50
    POSITIVE LOGITS
    complexContent
    0.53
    TypedDataSet
    0.53
     onCancelled
    0.52
    WriteLiteral
    0.52
     friendly
    0.52
    friendly
    0.50
    AddHtmlAttribute
    0.49
     desglose
    0.48
    iser
    0.48
     الرياضيه
    0.48
    Activations Density 1.519%

    No Known Activations