© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9427
    Prev
    Next
    INDEX
    Explanations

    numbers and letters in scientific publications from figures and tables, and dates written in short form

    oai_token-act-pair · gemini-2.0-flash

    abbreviations

    np_max-act · gemini-2.0-flash

    say "▁" Method used: 2 — because following tokens start with ▁ — say "▁"

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     تضيفلها
    -0.53
    九
    -0.52
    encodeWith
    -0.51
    WriteBarrier
    -0.48
    ↵↵
    -0.48
     五
    -0.48
     Five
    -0.47
     wireType
    -0.47
    9
    -0.47
     Gaulle
    -0.47
    POSITIVE LOGITS
     Febrero
    0.65
     Moors
    0.63
    Kool
    0.62
     lendemain
    0.60
     fevereiro
    0.60
    براير
    0.58
    MLLoader
    0.58
     BTU
    0.58
     Minder
    0.57
     crdi
    0.57
    Activations Density 4.419%

    No Known Activations