© 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. 9880
    Prev
    Next
    INDEX
    Explanations

    general words and phrases in French, possibly related to asking or offering assistance

    oai_token-act-pair · gemini-2.0-flash

    French technical discussions

    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
     laure
    -0.50
     Woo
    -0.49
     Seul
    -0.49
     Darum
    -0.47
     Wulf
    -0.47
     exempl
    -0.47
     lẫn
    -0.46
    Rujukan
    -0.46
     obstin
    -0.45
    Ayr
    -0.45
    POSITIVE LOGITS
     something
    1.16
     things
    1.16
     thing
    1.15
    Something
    1.14
     Something
    1.09
    Thing
    1.09
    thing
    1.07
    something
    1.06
    Things
    1.06
     what
    1.06
    Activations Density 0.404%

    No Known Activations