© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8094
    Prev
    Next
    INDEX
    Explanations

    words indicating separation, such as the boolean "or" and section divisions in the document

    oai_token-act-pair · gemini-2.0-flash

    "or" and alternatives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    WriteTagHelper
    -0.58
    enumi
    -0.56
     "..\..\
    -0.54
    snackbar
    -0.50
    TestingModule
    -0.49
    modelBuilder
    -0.48
     zawod
    -0.48
     volontà
    -0.48
     distanciation
    -0.47
    Disposed
    -0.46
    POSITIVE LOGITS
    anskje
    0.72
    AsUp
    0.63
     mostrarán
    0.60
     }{@
    0.59
    afficheront
    0.59
     Cataloging
    0.58
    AndEndTag
    0.56
    ViewImports
    0.56
     Reverso
    0.56
    septic
    0.55
    Activations Density 1.916%

    No Known Activations