© 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. 5510
    Prev
    Next
    INDEX
    Explanations

    the word "non" or "not,' especially when used in collocations such as "non-profit."

    oai_token-act-pair · gemini-2.0-flash

    non/not

    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
     transfieras
    -0.63
    webElementXpaths
    -0.62
     EconPapers
    -0.55
     themſelves
    -0.54
    ürzen
    -0.53
     organisation
    -0.52
     ſhe
    -0.52
     AssemblyProduct
    -0.52
    ás
    -0.50
     مث
    -0.50
    POSITIVE LOGITS
     профи
    0.52
    ufort
    0.50
     AppCompatTheme
    0.50
    aryen
    0.49
    dymyr
    0.48
    скажите
    0.48
    Distribución
    0.48
    ⋙
    0.44
    LabelTagHelper
    0.44
    FormTagHelper
    0.43
    Activations Density 0.300%

    No Known Activations