© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6860
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially those containing numbers and symbols

    oai_token-act-pair · gemini-2.0-flash

    archaic or uncommon English terms

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

    Code/technical documents

    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
     app
    -0.59
    <eos>
    -0.59
     M
    -0.56
     [
    -0.56
    mi
    -0.56
    app
    -0.55
     (
    -0.55
     m
    -0.53
     O
    -0.53
     Z
    -0.53
    POSITIVE LOGITS
     itſelf
    1.16
    aarrggbb
    1.13
     Monfieur
    1.12
     raiſ
    1.11
     pleaſure
    1.09
     myſelf
    1.09
     Theſe
    1.06
     uſed
    1.05
     houſe
    1.03
     faſt
    1.03
    Activations Density 29.536%

    No Known Activations