© 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. 12661
    Prev
    Next
    INDEX
    Explanations

    words related to clinical trial reporting, especially patient/year numbers, replicate counts, and treatment names

    oai_token-act-pair · gemini-2.0-flash

    experimental replicates and patients

    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
    нова
    -0.42
     Meeting
    -0.41
    M
    -0.39
    cm
    -0.39
     militare
    -0.38
    t
    -0.38
    頭に
    -0.38
    T
    -0.38
    proto
    -0.37
    end
    -0.37
    POSITIVE LOGITS
     חיצוניים
    0.98
     الرياضيه
    0.98
    __":
    0.97
     المعيارى
    0.96
     ddelweddau
    0.95
    .*")]
    0.91
     للاسماء
    0.90
    __':
    0.90
    SBATCH
    0.90
    tagHelperRunner
    0.90
    Activations Density 1.190%

    No Known Activations