© 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. 14093
    Prev
    Next
    INDEX
    Explanations

    the word "high" in technical documents

    oai_token-act-pair · gemini-2.0-flash

    high

    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
    Rüyada
    -0.82
    thâu
    -0.77
     <<<<<<<<<<<<<<
    -0.76
     дописавши
    -0.76
    UserScript
    -0.74
    ArrowToggle
    -0.72
    eabouts
    -0.71
    Geplaatst
    -0.71
    skjaer
    -0.70
     referenties
    -0.69
    POSITIVE LOGITS
     república
    0.56
    ↵↵
    0.56
    1
    0.54
     asesinado
    0.51
     Large
    0.50
     higher
    0.50
     sklo
    0.49
     vermelhas
    0.49
     mør
    0.49
     dår
    0.48
    Activations Density 0.168%

    No Known Activations