© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 364
    Prev
    Next
    INDEX
    Explanations

    words related to special or limited collections of items, like special editions and boxed sets

    oai_token-act-pair · gemini-2.0-flash

    edition set

    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
    Negative Logits
    تقاوى
    -0.67
    InjectAttribute
    -0.58
    WEAR
    -0.51
    tals
    -0.50
    rrggbb
    -0.50
    ้น
    -0.50
     незавершена
    -0.50
     middleware
    -0.50
    grin
    -0.49
    !(:
    -0.49
    POSITIVE LOGITS
    <bos>
    0.75
     متعلقه
    0.68
     بيها
    0.62
    SizeF
    0.59
     للمعارف
    0.57
     Laing
    0.56
    forChild
    0.56
     speciali
    0.55
     imageNamed
    0.55
     gallery
    0.54
    Activations Density 0.708%

    No Known Activations