© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7829
    Prev
    Next
    INDEX
    Explanations

    words of high importance in different contexts including code, Croatian language, and also the word "majesty."

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Reſ
    -0.67
     fubject
    -0.66
     Efq
    -0.62
     Houſe
    -0.61
     cauſe
    -0.60
     caufe
    -0.59
     itſelf
    -0.59
     reaſon
    -0.57
    casio
    -0.57
     houſe
    -0.57
    POSITIVE LOGITS
     me
    1.08
     him
    1.01
     us
    0.97
    <bos>
    0.95
    awtextra
    0.87
     Catawiki
    0.71
     Him
    0.71
     Me
    0.70
     onCreateView
    0.70
     you
    0.65
    Activations Density 1.033%

    No Known Activations