© 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. 1763
    Prev
    Next
    INDEX
    Explanations

    mentions of numbers, especially counting numbers, sometimes associated with legal contexts involving juries or items.

    oai_token-act-pair · gemini-2.0-flash

    references to quantities or numbers

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

    numbers

    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
     dieux
    -1.05
     enfans
    -0.96
     épaules
    -0.86
     larmes
    -0.84
     lèvres
    -0.83
     rayures
    -0.82
     bénéfices
    -0.82
     négociations
    -0.81
     âmes
    -0.81
     dépens
    -0.79
    POSITIVE LOGITS
     separate
    0.73
     or
    0.70
     different
    0.69
     pieces
    0.62
     things
    0.61
     versions
    0.60
     кӀ
    0.58
     courses
    0.57
     members
    0.57
     sections
    0.55
    Activations Density 2.870%

    No Known Activations