© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1740
    Prev
    Next
    INDEX
    Explanations

    a number of words that collocate with 'couple' or the concepts of numbers and quantities.

    oai_token-act-pair · gemini-2.0-flash

    couple

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     souri
    -0.56
     OnInit
    -0.55
     cucchiai
    -0.55
     humaine
    -0.53
    addImage
    -0.50
     humain
    -0.49
     миллионов
    -0.46
     raffredd
    -0.46
    getPackageName
    -0.44
     adev
    -0.44
    POSITIVE LOGITS
     ModelExpression
    0.88
    tagHelperRunner
    0.83
     समीक्षक
    0.79
    IsMutable
    0.74
     >=",
    0.73
    queryInterface
    0.73
    MLLoader
    0.71
     himo
    0.69
    StoryboardSegue
    0.69
    /**
    0.66
    Activations Density 3.273%

    No Known Activations