© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10383
    Prev
    Next
    INDEX
    Explanations

    the word "much" and context around it, especially when it indicates a surprising quantity or degree

    oai_token-act-pair · gemini-2.0-flash

    much

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pingback
    -0.73
    doctype
    -0.55
     jadx
    -0.54
    thma
    -0.50
    ages
    -0.50
    الغ
    -0.49
     виправивши
    -0.49
     broek
    -0.48
    HasAnnotation
    -0.48
     العاده
    -0.47
    POSITIVE LOGITS
     simpler
    0.67
    più
    0.60
     olika
    0.60
    Geplaatst
    0.60
     sooner
    0.59
     earlier
    0.59
     later
    0.57
     more
    0.57
     different
    0.57
    different
    0.57
    Activations Density 1.061%

    No Known Activations