© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6964
    Prev
    Next
    INDEX
    Explanations

    words associated with art exhibitions, museums, galleries, and artist names.

    oai_token-act-pair · gemini-2.0-flash

    show

    np_max-act-logits · 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
    principalTable
    -0.54
    potranspiration
    -0.50
     resourceCulture
    -0.44
     EconPapers
    -0.42
    transQ
    -0.41
    RegressionTest
    -0.41
    farlane
    -0.40
    dflare
    -0.40
    MetaObject
    -0.40
    legi
    -0.40
    POSITIVE LOGITS
     show
    2.22
     Show
    1.98
    show
    1.95
    Show
    1.91
     SHOW
    1.84
     shows
    1.83
     showing
    1.79
     display
    1.77
     exhibit
    1.75
     exhibiting
    1.75
    Activations Density 1.547%

    No Known Activations