© 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. 2952
    Prev
    Next
    INDEX
    Explanations

    references to a court of law, citizenship or the State

    oai_token-act-pair · gemini-2.0-flash

    court

    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
     Theſe
    -1.02
     myſelf
    -0.98
     itſelf
    -0.96
     themſelves
    -0.94
     Jefus
    -0.93
     Shakspeare
    -0.90
     ―――――
    -0.86
     ſeveral
    -0.85
     Majefty
    -0.85
     Monfieur
    -0.85
    POSITIVE LOGITS
    setVerticalGroup
    0.86
    InjectAttribute
    0.67
     that
    0.65
    SPATH
    0.62
    mybatisplus
    0.60
     not
    0.54
     also
    0.52
    ду
    0.52
     kalori
    0.51
    ↵↵
    0.50
    Activations Density 0.986%

    No Known Activations