© 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. 15319
    Prev
    Next
    INDEX
    Explanations

    the letters 'p', 'r', 'c', 'v' and 'q' next to other letters or symbols in code or math formulas, or numbers

    oai_token-act-pair · gemini-2.0-flash

    foreign language words or phrases

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

    say "letter p"

    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
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.66
    protoc
    -0.63
    Buildable
    -0.60
    IndentedString
    -0.56
    runApp
    -0.56
    hoeddwyd
    -0.55
     panoramique
    -0.55
    oneofs
    -0.54
     OMITBAD
    -0.54
     contextLoads
    -0.53
    POSITIVE LOGITS
    Fordítás
    0.46
     Differ
    0.45
     تضيفلها
    0.45
    غی
    0.44
    ciel
    0.44
     Avril
    0.43
    紀
    0.43
     Lio
    0.43
     Henrique
    0.42
     reiz
    0.42
    Activations Density 1.476%

    No Known Activations