© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13377
    Prev
    Next
    INDEX
    Explanations

    the phrase "primary care"

    oai_token-act-pair · gemini-2.0-flash

    terms related to primary care

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

    primary

    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
    GEBURTSDATUM
    -0.72
    Clik
    -0.71
    matchCondition
    -0.66
     Reverso
    -0.61
    存于互联网档案馆
    -0.60
    SharedCtor
    -0.60
    niająca
    -0.57
     crdi
    -0.57
    MENAFN
    -0.56
    Pratique
    -0.56
    POSITIVE LOGITS
     industry
    0.54
     Industry
    0.52
     res
    0.50
     reg
    0.50
     level
    0.50
    тератур
    0.49
     INDUSTRY
    0.49
    ooper
    0.49
     getApplication
    0.47
    业
    0.47
    Activations Density 3.492%

    No Known Activations