© 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. 1624
    Prev
    Next
    INDEX
    Explanations

    words related to methods, techniques, or approaches

    oai_token-act-pair · gemini-2.0-flash

    ways

    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
     ways
    -0.98
     Ways
    -0.72
     WAYS
    -0.71
    Ways
    -0.69
     manières
    -0.54
    ways
    -0.53
    WAYS
    -0.52
     maneiras
    -0.49
    спи
    -0.47
     façons
    -0.46
    POSITIVE LOGITS
    
    0.95
     Xunit
    0.75
    ValueStyle
    0.73
    StoryboardSegue
    0.71
     ComVisible
    0.70
     وتسجيلات
    0.68
     XCTest
    0.64
     Catawiki
    0.63
    ApiOperation
    0.63
    Portale
    0.63
    Activations Density 16.547%

    No Known Activations