© 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. 15429
    Prev
    Next
    INDEX
    Explanations

    words that modify nouns suggesting some measure of quantity or possession

    oai_token-act-pair · gemini-2.0-flash

    words indicating quantity or variety

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

    many

    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
    -0.72
     genoux
    -0.72
     épaules
    -0.69
     vérit
    -0.67
     nuages
    -0.64
     vœux
    -0.63
     prêtres
    -0.62
     bénéfices
    -0.60
    ValueGeneration
    -0.59
     oiseaux
    -0.57
    POSITIVE LOGITS
     cases
    0.68
     sources
    0.60
     expressions
    0.59
     clues
    0.56
     different
    0.56
     accounts
    0.55
     versions
    0.54
     reasons
    0.54
     incidents
    0.54
     instances
    0.54
    Activations Density 2.183%

    No Known Activations