© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4014
    Prev
    Next
    INDEX
    Explanations

    words related to food, especially dishes and ingredients from Middle Eastern and Asian cuisines.

    oai_token-act-pair · gemini-2.0-flash

    technical or programming-related keywords

    np_token-act-pair-logits · gpt-4o-mini

    food reviews/recipes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     kasarigan
    -0.56
     actionBar
    -0.56
     createState
    -0.55
    ์
    -0.52
    EMIA
    -0.49
    aktery
    -0.49
     Насе
    -0.49
    seitige
    -0.47
    cency
    -0.47
    idered
    -0.47
    POSITIVE LOGITS
    SequentialGroup
    0.68
    GEBURTSDATUM
    0.66
     utafitiHapana
    0.61
    RegressionTest
    0.61
     ModelExpression
    0.59
    SpringRunner
    0.51
    ImageContext
    0.50
     newBuilder
    0.49
    routeProvider
    0.49
     PhpStorm
    0.49
    Activations Density 0.715%

    No Known Activations