© 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. 13192
    Prev
    Next
    INDEX
    Explanations

    legal language related to supreme court rulings and processes

    oai_token-act-pair · gemini-2.0-flash

    Supreme

    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
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.98
     Anſ
    -0.95
     Reſ
    -0.94
     Houſe
    -0.94
     Monfieur
    -0.91
     Theſe
    -0.91
    ſelf
    -0.90
     Diſ
    -0.85
    ſelves
    -0.84
     Verſ
    -0.84
    POSITIVE LOGITS
     surla
    0.62
     "
    0.61
     He
    0.59
     Ar
    0.56
     His
    0.56
    verwijspagina
    0.55
    ↵↵
    0.55
     I
    0.54
     document
    0.52
     But
    0.52
    Activations Density 1.766%

    No Known Activations