© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 5007
    Prev
    Next
    INDEX
    Explanations

    legal jargon regarding trials and court decisions

    oai_token-act-pair · gemini-2.0-flash

    legal proceedings and opportunities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    tvguidetime
    -0.86
    PMailer
    -0.85
     BoxFit
    -0.84
    StoryboardSegue
    -0.83
    featureID
    -0.82
    HtmlAttribute
    -0.75
    BufferException
    -0.75
    RenderAtEndOf
    -0.72
    TargetException
    -0.70
     Paglinawan
    -0.70
    POSITIVE LOGITS
     éditoriale
    0.51
     replacement
    0.50
     recovery
    0.49
     restored
    0.49
     replace
    0.46
     rempla
    0.46
     restauration
    0.45
     recovering
    0.45
     Recovery
    0.44
     Restore
    0.44
    Activations Density 1.506%

    No Known Activations