© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14373
    Prev
    Next
    INDEX
    Explanations

    technical words found in medical and biological research papers

    oai_token-act-pair · gemini-2.0-flash

    patients

    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
     pazienti
    -0.76
     médical
    -0.72
     lekar
    -0.72
     clínico
    -0.72
     PATIENT
    -0.71
     patients
    -0.70
     clinically
    -0.70
     médicaux
    -0.69
     CLINICAL
    -0.68
     pacientes
    -0.68
    POSITIVE LOGITS
    ReusableCell
    0.71
    DoubleQuotes
    0.61
     مشين
    0.59
     Business
    0.57
     estekak
    0.57
     Ge
    0.56
    himovic
    0.54
    ADO
    0.54
     Da
    0.53
    ANDUM
    0.52
    Activations Density 5.650%

    No Known Activations