© 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. 399
    Prev
    Next
    INDEX
    Explanations

    computer-related terms such as software products, log data, or operating systems and their components

    oai_token-act-pair · gemini-2.0-flash
    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
    DoubleQuotes
    -0.93
    hyrchwyd
    -0.87
    expandindo
    -0.86
     ModelExpression
    -0.84
    WithIOException
    -0.84
    aarrggbb
    -0.82
     صوتيه
    -0.82
     الحره
    -0.80
     يتيمه
    -0.79
     intptr
    -0.75
    POSITIVE LOGITS
    <bos>
    0.57
     norske
    0.44
     rosse
    0.42
    Tal
    0.41
     hosts
    0.40
    ποίη
    0.40
     rojas
    0.40
     bianche
    0.39
    ב
    0.38
    ínico
    0.37
    Activations Density 1.194%

    No Known Activations