© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6689
    Prev
    Next
    INDEX
    Explanations

    words that relate to surgery and medical procedures

    oai_token-act-pair · gemini-2.0-flash

    surgeries and medical procedures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     autorytatywna
    -0.92
     propOrder
    -0.88
     nakalista
    -0.87
     myſelf
    -0.83
     الحره
    -0.82
    bibfield
    -0.80
    NUMX
    -0.80
     itſelf
    -0.79
     fubject
    -0.79
     ſtate
    -0.76
    POSITIVE LOGITS
     patients
    0.78
     patient
    0.66
     Patients
    0.63
     surgery
    0.63
     hospital
    0.61
     pacientes
    0.61
     Patient
    0.60
     Patienten
    0.58
    Patient
    0.58
     doctors
    0.57
    Activations Density 5.064%

    No Known Activations