© 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. 9280
    Prev
    Next
    INDEX
    Explanations

    words in a variety of technical contexts

    oai_token-act-pair · 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
     Reverso
    -0.75
    parsedMessage
    -0.67
    GOTREF
    -0.56
    Sucesor
    -0.56
     Actor
    -0.56
    ành
    -0.55
    Actor
    -0.55
     actor
    -0.52
    actor
    -0.52
    ViewFeatures
    -0.51
    POSITIVE LOGITS
    UnknownFieldSet
    0.55
    UVEN
    0.54
    PendingIntent
    0.54
    offsetof
    0.53
    grano
    0.47
     subsistence
    0.47
    javadoc
    0.46
    engelsk
    0.45
     fetus
    0.45
     AssemblyTitle
    0.45
    Activations Density 9.668%

    No Known Activations