© 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. 10231
    Prev
    Next
    INDEX
    Explanations

    code snippets and code-related terms

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    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
    Negative Logits
     pleaſure
    -0.82
     بيها
    -0.81
     purpoſe
    -0.79
     houſe
    -0.76
     Houſe
    -0.72
     Reſ
    -0.71
     ſmall
    -0.68
    存于互联网档案馆
    -0.68
     Majefty
    -0.67
     ſeveral
    -0.65
    POSITIVE LOGITS
     code
    0.58
    代码
    0.49
    Afficher
    0.49
    コード
    0.48
    code
    0.48
    webElementXpaths
    0.45
    克拉
    0.42
    Code
    0.42
     armado
    0.42
    ulli
    0.41
    Activations Density 2.224%

    No Known Activations