© 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. 10358
    Prev
    Next
    INDEX
    Explanations

    numbers in parentheses, especially percentages and statistics

    oai_token-act-pair · gemini-2.0-flash

    ordinal numbers

    np_max-act-logits · gemini-2.0-flash

    say "digits"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    Not in Any Lists

    No Comments

    Negative Logits
     Wednesday
    -0.91
    Wednesday
    -0.89
    3
    -0.77
     WEDNESDAY
    -0.76
     الأربع
    -0.72
     quarta
    -0.71
     trio
    -0.70
     Thursday
    -0.70
     Wednesdays
    -0.69
     miércoles
    -0.68
    POSITIVE LOGITS
    ParallelGroup
    0.74
     eighth
    0.71
     Satur
    0.71
     seventh
    0.69
     Eighth
    0.68
     ninth
    0.66
     Saturday
    0.66
     Seventh
    0.65
    atguigu
    0.65
    UnusedPrivate
    0.65
    Activations Density 2.001%

    No Known Activations