© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12958
    Prev
    Next
    INDEX
    Explanations

    mentions of medicine, pharmaceuticals, and traditional Chinese medicine

    oai_token-act-pair · gemini-2.0-flash

    medicine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     medicine
    -2.38
     Medicine
    -2.17
    Medicine
    -2.02
     MEDICINE
    -1.91
    medicine
    -1.89
     medicines
    -1.45
     medication
    -1.27
     Medicines
    -1.22
     medicina
    -1.10
     Medication
    -1.10
    POSITIVE LOGITS
    
    0.69
     ***!
    0.60
     detik
    0.57
    ultuous
    0.55
    tagHelperRunner
    0.55
    গ্রহ
    0.55
     forhold
    0.55
    umably
    0.53
    styleable
    0.52
    Hentet
    0.52
    Activations Density 1.085%

    No Known Activations