© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4677
    Prev
    Next
    INDEX
    Explanations

    words directly related to health programs, primarily HIV/AIDS and malaria, and their management

    oai_token-act-pair · gemini-2.0-flash

    healthcare and medicine

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     >",
    -0.56
    }))
    -0.56
    AddTagHelper
    -0.52
     AssemblyTitle
    -0.52
     Taktlose
    -0.49
    rily
    -0.48
    hopped
    -0.48
    TypedDataSet
    -0.47
    labelledby
    -0.47
    )։
    -0.46
    POSITIVE LOGITS
    secta
    0.57
    quelize
    0.57
    setupUi
    0.53
    endpush
    0.52
     aDecoder
    0.52
     pstmt
    0.52
    sune
    0.50
     ultrasonic
    0.50
     fibrosis
    0.49
    ριά
    0.49
    Activations Density 8.652%

    No Known Activations