© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 5000
    Prev
    Next
    INDEX
    Explanations

    terms related to immunology, especially cytokines, cells of the immune system, and allergic inflammation.

    oai_token-act-pair · gemini-2.0-flash

    T cells and immune response

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     EconPapers
    -1.09
    ########.
    -0.94
    ValueStyle
    -0.91
    tvguidetime
    -0.90
     betweenstory
    -0.90
    expandindo
    -0.87
    TypedDataSet
    -0.84
    featureID
    -0.81
    Jereo
    -0.81
     ligiloj
    -0.80
    POSITIVE LOGITS
     vyst
    0.44
    osene
    0.44
    appi
    0.42
     sikap
    0.41
     datter
    0.40
    에서
    0.39
     without
    0.39
    rof
    0.39
    Calling
    0.38
     questão
    0.38
    Activations Density 1.657%

    No Known Activations