© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10045
    Prev
    Next
    INDEX
    Explanations

    variations of 'Or' and the letters following

    oai_token-act-pair · gemini-2.0-flash

    or

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ikiki
    -0.58
     naselje
    -0.57
     action
    -0.55
     :(
    -0.55
    zana
    -0.54
    헌
    -0.54
     Construcción
    -0.53
     PEP
    -0.52
    action
    -0.52
     Depor
    -0.52
    POSITIVE LOGITS
    లాలు
    0.65
    parsedMessage
    0.55
    Personendaten
    0.53
     فريبيس
    0.52
    
    0.50
     تكبرها
    0.50
    Autoritní
    0.49
    商品説明
    0.46
    :✨
    0.46
     ApiException
    0.45
    Activations Density 0.301%

    No Known Activations