© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10186
    Prev
    Next
    INDEX
    Explanations

    words associated with traditional medicine, especially of Thai or Ayurvedic origin.

    oai_token-act-pair · gemini-2.0-flash

    Medicine/herbal research

    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
    OGND
    -0.56
     ympä
    -0.50
     '{{
    -0.48
     scopo
    -0.47
     فريبيس
    -0.45
     álla
    -0.45
    氯
    -0.44
    Closeable
    -0.43
     finestra
    -0.43
     distribuição
    -0.42
    POSITIVE LOGITS
    ArgumentParser
    0.66
    Gambas
    0.60
     uſed
    0.59
    Personendaten
    0.59
    GraphicsUnit
    0.59
    ItemBackground
    0.58
     pleaſure
    0.58
    httphttps
    0.57
     isComment
    0.57
    InvalidProtocol
    0.57
    Activations Density 1.479%

    No Known Activations