© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4946
    Prev
    Next
    INDEX
    Explanations

    general references to healthcare facilities, especially hospitals and centers

    oai_token-act-pair · gemini-2.0-flash

    Medical terms

    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
     betweenstory
    -0.88
    expandindo
    -0.78
     ModelExpression
    -0.77
     unknownFields
    -0.72
     <>",
    -0.68
    LabelTagHelper
    -0.67
     incomplète
    -0.65
    yntaxException
    -0.63
     ostavi
    -0.60
     eventdata
    -0.60
    POSITIVE LOGITS
     Cancer
    0.47
    boutin
    0.46
    SequentialGroup
    0.45
     trauma
    0.44
    hio
    0.43
    Osc
    0.41
    leby
    0.40
     cancer
    0.40
    GetChild
    0.40
    uxxxx
    0.40
    Activations Density 1.002%

    No Known Activations