© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4610
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
    findpost
    -0.90
     EconPapers
    -0.87
    Хьажоргаш
    -0.84
    الحياه
    -0.77
    Архівовано
    -0.75
    BeginInit
    -0.71
     كومونز
    -0.71
     and
    -0.71
    تقاوى
    -0.70
     ویکی‌پدیا
    -0.69
    POSITIVE LOGITS
    ,
    1.34
    、
    0.68
    -,
    0.49
    ﹑
    0.47
    ､
    0.42
    ,\,
    0.40
    NSYLVANIA
    0.40
    _,
    0.39
    ・
    0.39
    ?,?,
    0.37
    Activations Density 7.324%

    No Known Activations