© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14823
    Prev
    Next
    INDEX
    Explanations

    numbers, dates, and quantities

    oai_token-act-pair · gemini-2.0-flash

    punctuation and numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ton
    -0.44
    żd
    -0.41
     tour
    -0.40
    <bos>
    -0.40
    onies
    -0.40
    Wart
    -0.40
     tengah
    -0.39
    läs
    -0.39
    allu
    -0.38
    kle
    -0.38
    POSITIVE LOGITS
     <=",
    0.90
     AssemblyCulture
    0.88
    ngdoc
    0.78
     تضيفلها
    0.77
     Италијани
    0.77
     CreateTagHelper
    0.72
     trajets
    0.70
    DockStyle
    0.66
    хьтан
    0.66
     ویکی‌پدیای
    0.66
    Activations Density 3.976%

    No Known Activations