© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12474
    Prev
    Next
    INDEX
    Explanations

    mentions of hospitals and medical care situations

    oai_token-act-pair · gemini-2.0-flash

    hospital

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     hospital
    -2.11
     Hospital
    -2.03
    Hospital
    -1.89
    hospital
    -1.70
     HOSPITAL
    -1.68
     hospitals
    -1.57
     Hospitals
    -1.37
     hospitalization
    -1.22
    Hospitals
    -1.16
     hospitalized
    -1.13
    POSITIVE LOGITS
    󠁴
    0.84
     AssemblyProduct
    0.75
    SequentialGroup
    0.72
    Personendaten
    0.64
    routeProvider
    0.64
    TemporalType
    0.63
     اكتوبر
    0.61
    maar
    0.60
    ADELPHIA
    0.60
    gründet
    0.59
    Activations Density 2.869%

    No Known Activations