© 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. 14014
    Prev
    Next
    INDEX
    Explanations

    words and letters commonly found in scientific documents related to biology

    oai_token-act-pair · gemini-2.0-flash

    GA

    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
    GA
    -0.85
    ga
    -0.72
    Ga
    -0.63
    zi
    -0.63
    MinWidth
    -0.56
     digress
    -0.55
     ga
    -0.49
     Concurrent
    -0.49
    tigste
    -0.49
     rağmen
    -0.49
    POSITIVE LOGITS
     autorytatywna
    0.92
    Jereo
    0.68
    WebServlet
    0.65
    WithIOException
    0.65
    Cyfeiriadau
    0.63
    
    0.63
     nahilalakip
    0.63
     propOrder
    0.61
    VIAF
    0.61
    verifyException
    0.60
    Activations Density 8.689%

    No Known Activations