© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13478
    Prev
    Next
    INDEX
    Explanations

    legal language describing real or intellectual property

    oai_token-act-pair · gemini-2.0-flash

    property

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     تضيفلها
    -0.93
    IsContent
    -0.91
     beginnetje
    -0.84
     ModelExpression
    -0.81
    setVerticalGroup
    -0.78
    ″]
    -0.74
    ()]
    -0.71
     كومونز
    -0.71
    Biographie
    -0.69
    enderror
    -0.69
    POSITIVE LOGITS
     termica
    0.86
     réparation
    0.82
     électriques
    0.81
     térmica
    0.80
     démocr
    0.77
     desorption
    0.77
     coscienza
    0.77
     lumineuse
    0.77
     traitors
    0.76
     indépendante
    0.76
    Activations Density 2.730%

    No Known Activations