© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16374
    Prev
    Next
    INDEX
    Explanations

    the word "nation"

    oai_token-act-pair · gemini-2.0-flash

    nation

    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
    +#+#
    -0.92
     ویکی‌پدیای
    -0.84
    IntoConstraints
    -0.82
     виправивши
    -0.82
     дописавши
    -0.73
     مرئيه
    -0.68
    jestel
    -0.68
     beginnetje
    -0.67
    IsContent
    -0.66
    makeConstraints
    -0.65
    POSITIVE LOGITS
     näm
    0.67
     übrigens
    0.62
     vänt
    0.59
    <blockquote>
    0.58
     kanyang
    0.58
    τουργ
    0.57
     coraggio
    0.57
     paraître
    0.57
     imidlertid
    0.56
     Gegenteil
    0.55
    Activations Density 0.363%

    No Known Activations