© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14875
    Prev
    Next
    INDEX
    Explanations

    words connected to medical or legal processes

    oai_token-act-pair · gemini-2.0-flash

    medical context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     medical
    -2.20
     Medical
    -2.16
    Medical
    -2.09
    medical
    -2.02
     hospital
    -1.95
     MEDICAL
    -1.95
     medically
    -1.94
     doctors
    -1.92
    MEDICAL
    -1.90
     Hospital
    -1.85
    POSITIVE LOGITS
     lenker
    0.50
     שוליים
    0.49
    chenkt
    0.46
    kheim
    0.43
     useAppContext
    0.43
     الحره
    0.43
    Hozzáférés
    0.43
    scrapy
    0.41
    styleType
    0.41
    eseorang
    0.41
    Activations Density 3.562%

    No Known Activations