© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3991
    Prev
    Next
    INDEX
    Explanations

    words related to website development and testing

    oai_token-act-pair · gemini-2.0-flash

    live

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     betweenstory
    -1.01
    webElementXpaths
    -0.98
    AccessFile
    -0.95
     ligiloj
    -0.93
    makeConstraints
    -0.92
    ConstraintMaker
    -0.92
    évaluateur
    -0.91
    HasAnnotation
    -0.87
    ImageContext
    -0.86
    TagMode
    -0.85
    POSITIVE LOGITS
     live
    2.28
    live
    1.95
     Live
    1.73
    Live
    1.69
     LIVE
    1.66
    LIVE
    1.55
     living
    0.95
    ライブ
    0.94
     živ
    0.93
     lived
    0.88
    Activations Density 1.451%

    No Known Activations