© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1549
    Prev
    Next
    INDEX
    Explanations

    capitalized initials and numbers in the middle of sentences, possibly identifying citations

    oai_token-act-pair · gemini-2.0-flash

    varied linguistic tokens from multiple languages

    np_token-act-pair-logits · gpt-4o-mini

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    wikimedia
    -0.54
    liani
    -0.52
    hubung
    -0.47
    انگلیسی
    -0.46
    RTLD
    -0.45
     Gegenteil
    -0.44
    teman
    -0.43
    ptonshire
    -0.42
     obstante
    -0.42
    hawatir
    -0.42
    POSITIVE LOGITS
     оригіналу
    0.75
     للاسماء
    0.67
     Roskov
    0.66
    脚注の使い方
    0.65
     nahilalakip
    0.64
     Económica
    0.64
     виправивши
    0.60
     lenker
    0.58
    enumi
    0.58
    ocarditis
    0.57
    Activations Density 3.269%

    No Known Activations