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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15086
    Prev
    Next
    INDEX
    Explanations

    numbers, especially percentages, ratios, and numerical data

    oai_token-act-pair · gemini-2.0-flash

    Statistics and percentages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     hundred
    -1.15
    hundred
    -1.09
     fifty
    -0.98
     Hundred
    -0.95
    Hundred
    -0.93
     half
    -0.86
     hundert
    -0.81
     thirty
    -0.79
    fifty
    -0.79
     HUND
    -0.76
    POSITIVE LOGITS
     виправивши
    0.87
     protoimpl
    0.67
    VersionUID
    0.60
    存于互联网档案馆
    0.60
     الاطلاع
    0.59
     vPvB
    0.55
     ویکی‌پدی
    0.55
     архивлан
    0.54
     springfox
    0.54
    bufio
    0.52
    Activations Density 1.758%

    No Known Activations