© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4922
    Prev
    Next
    INDEX
    Explanations

    words relating to waste, reusing materials, and environmental awareness alongside words relating to commerce such as prices or goods.

    oai_token-act-pair · gemini-2.0-flash

    recycling and reusing items

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    roix
    -0.55
    Biografia
    -0.53
    EnableWeb
    -0.49
      
    -0.47
    hilation
    -0.46
    localctx
    -0.45
    捗
    -0.44
    kuuta
    -0.44
    ěstí
    -0.44
    ufact
    -0.44
    POSITIVE LOGITS
     propOrder
    0.68
     Concession
    0.57
    lukan
    0.57
    Autoritní
    0.56
     Mandate
    0.54
     pegs
    0.54
    Viited
    0.54
    MOM
    0.53
    GTCX
    0.53
     hemma
    0.52
    Activations Density 34.387%

    No Known Activations