© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13173
    Prev
    Next
    INDEX
    Explanations

    code, diffs, logs, and numerical data, especially when they appear with line numbers and file paths

    oai_token-act-pair · gemini-2.0-flash

    lines of 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
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.74
     فريبيس
    -0.71
    GraphicsUnit
    -0.68
    yntaxException
    -0.68
     متعلقه
    -0.68
     ujednoznacz
    -0.68
    énario
    -0.67
    :✨
    -0.66
     HasFactory
    -0.66
     '\\;'
    -0.65
    POSITIVE LOGITS
     miglia
    0.54
     uſ
    0.54
    Thousands
    0.54
     Thousands
    0.53
     quæ
    0.52
     ſmall
    0.52
     thousands
    0.51
     ſeveral
    0.51
     beſ
    0.50
     beſt
    0.49
    Activations Density 24.909%

    No Known Activations