© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1681
    Prev
    Next
    INDEX
    Explanations

    words related to position or location, especially those related to the top or back

    oai_token-act-pair · gemini-2.0-flash

    tokens related to structure or organization

    np_token-act-pair-logits · gpt-4o-mini

    spatial positions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     disambiguazione
    -1.02
    expandindo
    -0.84
     Chwiliwch
    -0.83
     Paglinawan
    -0.83
    writeFieldEnd
    -0.80
     مرئيه
    -0.78
     تضيفلها
    -0.75
     للاسماء
    -0.72
     дописавши
    -0.71
    AntiForgeryToken
    -0.66
    POSITIVE LOGITS
     of
    1.12
     rangs
    0.58
    nameof
    0.53
    PackageManager
    0.52
     eorum
    0.52
    DialogInterface
    0.52
    ของ
    0.52
    occasione
    0.50
     ejus
    0.49
    kkelen
    0.49
    Activations Density 11.254%

    No Known Activations