© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14588
    Prev
    Next
    INDEX
    Explanations

    words in legal or technical contexts related to patents

    oai_token-act-pair · gemini-2.0-flash

    patent, copyright, intellectual

    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
    path
    -0.47
    setVerticalGroup
    -0.44
    mi
    -0.43
    olle
    -0.40
     Natal
    -0.40
    ns
    -0.40
    vo
    -0.40
    वे
    -0.40
    roll
    -0.39
    des
    -0.39
    POSITIVE LOGITS
    IUrlHelper
    0.79
    setupUi
    0.73
    twimg
    0.73
    Personensuche
    0.67
    RegressionTest
    0.65
    webElementXpaths
    0.64
    colgante
    0.64
    errHandler
    0.63
     дописавши
    0.62
    LookAnd
    0.62
    Activations Density 1.191%

    No Known Activations