© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13913
    Prev
    Next
    INDEX
    Explanations

    the word "which", sometimes with a slight boost to the word "composition"

    oai_token-act-pair · gemini-2.0-flash

    which

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    IsPostBack
    -0.60
     onPostExecute
    -0.57
     which
    -0.52
     prossimo
    -0.50
    sonder
    -0.50
    WritableDatabase
    -0.49
    Бележки
    -0.49
    erschein
    -0.49
    bidities
    -0.48
     tatuagens
    -0.48
    POSITIVE LOGITS
     Where
    0.73
    setViewportView
    0.72
    Where
    0.72
     Onde
    0.70
     Où
    0.70
     où
    0.69
    where
    0.68
    ImageContext
    0.68
    donde
    0.68
    +#+#
    0.67
    Activations Density 0.224%

    No Known Activations