© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 569
    Prev
    Next
    INDEX
    Explanations

    descriptions of architectural features

    oai_token-act-pair · gemini-2.0-flash

    architecture and history

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    tagHelperRunner
    -1.31
    aarrggbb
    -0.73
    EndContext
    -0.68
    JspWriter
    -0.65
    Fordítás
    -0.64
    WithMany
    -0.63
    tagext
    -0.63
     Plage
    -0.62
     المعيارى
    -0.59
    ariste
    -0.57
    POSITIVE LOGITS
    şı
    0.52
    ofman
    0.52
    treat
    0.49
     treated
    0.47
     TREAT
    0.45
     treating
    0.43
     Arbitration
    0.43
    ramide
    0.43
     step
    0.43
     stepped
    0.43
    Activations Density 2.274%

    No Known Activations