© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13551
    Prev
    Next
    INDEX
    Explanations

    the word "complex" and variations.

    oai_token-act-pair · gemini-2.0-flash

    complex

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     bolig
    -0.66
    massen
    -0.60
     cykel
    -0.59
    ergies
    -0.57
     määrä
    -0.56
     nødven
    -0.56
     enfans
    -0.55
    ambung
    -0.55
     littéraire
    -0.55
     abroad
    -0.55
    POSITIVE LOGITS
    __":
    0.81
    <bos>
    0.72
    styleable
    0.71
     AssemblyCulture
    0.70
    AccessorTable
    0.67
    uxxxx
    0.67
     @"/
    0.67
     CreateTagHelper
    0.66
    はじめに
    0.66
    */].
    0.65
    Activations Density 1.472%

    No Known Activations