© 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. 13578
    Prev
    Next
    INDEX
    Explanations

    words that appear in legal or bureaucratic documents

    oai_token-act-pair · gemini-2.0-flash

    Coding/text processing

    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
     épaules
    -0.54
     الاطلاع
    -0.48
    webElementXpaths
    -0.47
     FetchType
    -0.47
    form
    -0.46
    ツ
    -0.45
     handen
    -0.44
    ungsver
    -0.44
    telar
    -0.42
     úrov
    -0.42
    POSITIVE LOGITS
     surla
    0.86
    contentLoaded
    0.78
    BeginContext
    0.74
    клопе
    0.67
    asgi
    0.64
     betweenstory
    0.63
     continúas
    0.62
     "..\..\
    0.62
     raiſ
    0.60
     "..\..\..\
    0.60
    Activations Density 4.921%

    No Known Activations