© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5505
    Prev
    Next
    INDEX
    Explanations

    This neuron strongly activates on texts that seem to be excerpts from medical reports, especially those concerning experiments, surgeries, or microscopic examinations.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Fifty
    -0.83
    Twelve
    -0.82
     Савезне
    -0.74
    Forty
    -0.71
    Sixty
    -0.71
    Twenty
    -0.70
    Thirty
    -0.69
     Fifty
    -0.69
     ویکی‌پدیای
    -0.69
    SequentialGroup
    -0.67
    POSITIVE LOGITS
     
    1.55
     $
    0.63
    |}{$
    0.62
    1
    0.60
    2
    0.57
    3
    0.51
    achios
    0.50
    asable
    0.47
    typeorm
    0.47
    dimento
    0.47
    Activations Density 3.754%

    No Known Activations