© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13923
    Prev
    Next
    INDEX
    Explanations

    the word "importance" and related mathematical or scientific terms

    oai_token-act-pair · gemini-2.0-flash

    importance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     importance
    -0.65
     Effect
    -0.65
     Beek
    -0.62
     effect
    -0.62
     ramifications
    -0.57
     Slavic
    -0.57
     Eud
    -0.56
     PAL
    -0.56
    contentLoaded
    -0.56
     Bantu
    -0.56
    POSITIVE LOGITS
     chré
    0.86
     pauv
    0.71
     tombé
    0.70
     дописавши
    0.69
     fausse
    0.69
     circonst
    0.67
    AndEndTag
    0.66
     désol
    0.66
     échanti
    0.66
     vieilles
    0.66
    Activations Density 0.927%

    No Known Activations