© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4298
    Prev
    Next
    INDEX
    Explanations

    the word "not" and other negations

    oai_token-act-pair · gemini-2.0-flash

    not only

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     only
    -2.66
    only
    -2.41
    Only
    -2.39
     Only
    -2.25
    ONLY
    -1.88
     только
    -1.73
     seulement
    -1.68
     ONLY
    -1.62
     tylko
    -1.52
     jedynie
    -1.45
    POSITIVE LOGITS
    Sole
    0.73
     resourceCulture
    0.73
     arşivlendi
    0.67
     Sole
    0.60
    Kjelder
    0.58
     sole
    0.56
     <>",
    0.55
    queryInterface
    0.54
     solitary
    0.54
    forName
    0.53
    Activations Density 5.444%

    No Known Activations