© 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. 7228
    Prev
    Next
    INDEX
    Explanations

    words or short phrases that are used to make points or to illustrate an idea.

    oai_token-act-pair · gemini-2.0-flash

    one

    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
    Negative Logits
     varandra
    -0.63
    itemBuilder
    -0.59
    epam
    -0.52
     récon
    -0.52
     EconPapers
    -0.52
    drawSprites
    -0.51
     ktorí
    -0.51
    /$',
    -0.50
    +#+#
    -0.49
    setupUi
    -0.48
    POSITIVE LOGITS
    Clik
    0.71
    parsedMessage
    0.64
    roid
    0.55
    ww
    0.54
    imo
    0.53
    ype
    0.53
     chất
    0.53
    izen
    0.53
    udd
    0.52
    WebVitals
    0.52
    Activations Density 19.197%

    No Known Activations