© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2913
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to legal or regulatory issues, particularly concerning the FDA and pharmaceutical companies

    oai_token-act-pair · gemini-2.0-flash

    healthcare

    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
    Negative Logits
     admission
    -1.05
     admit
    -1.02
     admitted
    -1.01
     Admission
    -0.94
    Admission
    -0.92
     Admit
    -0.87
    admission
    -0.85
     admissions
    -0.83
     admitting
    -0.82
     admits
    -0.82
    POSITIVE LOGITS
     '\\;'
    0.82
     physicians
    0.80
     healthcare
    0.80
    IntoConstraints
    0.78
     clinicians
    0.76
     doctors
    0.71
    healthcare
    0.69
     clinician
    0.68
     practitioners
    0.66
     patient
    0.66
    Activations Density 6.792%

    No Known Activations