© 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. 14162
    Prev
    Next
    INDEX
    Explanations

    dates, durations, and references to timing in a legal context

    oai_token-act-pair · gemini-2.0-flash

    timely

    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
     myſelf
    -2.06
     Efq
    -1.97
     Jefus
    -1.75
     ſtate
    -1.70
     itſelf
    -1.70
     Theſe
    -1.69
     houſe
    -1.68
     themſelves
    -1.67
     whoſe
    -1.67
     Majefty
    -1.65
    POSITIVE LOGITS
     
    1.11
    ↵↵
    0.93
    ,
    0.92
     in
    0.90
      
    0.90
    ↵
    0.84
    <strong>
    0.83
     at
    0.81
     (
    0.79
     no
    0.77
    Activations Density 2.076%

    No Known Activations