© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5150
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to nerve blocks and surgical procedures

    oai_token-act-pair · gemini-2.0-flash

    medical terms related to surgical procedures

    np_token-act-pair-logits · gpt-4o-mini

    Medical surgical procedures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    новништво
    -0.62
    __':
    -0.56
     hObject
    -0.52
    __":
    -0.50
    Linki
    -0.49
    __":
    -0.48
    љено
    -0.45
     trái
    -0.44
    Примечания
    -0.44
    verz
    -0.44
    POSITIVE LOGITS
    SharedDtor
    0.67
    RunAsync
    0.63
    NamedQuery
    0.63
    webElementXpaths
    0.62
     AssemblyCompany
    0.61
     ligament
    0.57
    WillAppear
    0.56
     mobilization
    0.55
    Rüyada
    0.54
     tissue
    0.54
    Activations Density 16.652%

    No Known Activations