© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8198
    Prev
    Next
    INDEX
    Explanations

    the word "mess"

    oai_token-act-pair · gemini-2.0-flash

    mess

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     idéia
    -0.87
     figliu
    -0.86
     mukana
    -0.86
     bonté
    -0.85
     superiori
    -0.83
     supérieurs
    -0.83
     varandra
    -0.82
     gezond
    -0.81
     nationaux
    -0.80
     spéciaux
    -0.80
    POSITIVE LOGITS
     ویکی‌پدی
    0.90
     Roskov
    0.81
     autorytatywna
    0.77
     original
    0.74
    astéro
    0.74
    titleMargin
    0.73
     inc
    0.73
    цездатний
    0.72
     plan
    0.71
     les
    0.71
    Activations Density 1.105%

    No Known Activations