© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9333
    Prev
    Next
    INDEX
    Explanations

    academic journals, publishers, or legal codes and abbreviations

    oai_token-act-pair · gemini-2.0-flash

    publications and citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     outright
    -0.68
     downright
    -0.56
     straightforward
    -0.48
     blatant
    -0.48
     directly
    -0.46
     direct
    -0.45
     overt
    -0.44
     herself
    -0.44
     simply
    -0.44
     gross
    -0.43
    POSITIVE LOGITS
    CodedInputStream
    0.71
     XCTest
    0.68
    KommentareTeilen
    0.66
    참고
    0.65
    UserScript
    0.60
     насељу
    0.59
     DbSet
    0.58
    󠁢
    0.58
     INTERESAR
    0.57
     MotionEvent
    0.57
    Activations Density 0.915%

    No Known Activations