© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5135
    Prev
    Next
    INDEX
    Explanations

    web addresses

    oai_token-act-pair · gemini-2.0-flash

    www

    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
    vil
    -0.54
    lat
    -0.52
     for
    -0.50
    arch
    -0.49
     lat
    -0.48
     dur
    -0.47
    退
    -0.47
     Hardware
    -0.46
    Marne
    -0.46
     
    -0.46
    POSITIVE LOGITS
    InjectAttribute
    0.88
     تضيفلها
    0.88
     متعلقه
    0.86
     ModelExpression
    0.83
     Paglinawan
    0.80
    interopRequire
    0.78
    ItemBackground
    0.77
     Савезне
    0.75
    AutoScale
    0.75
     unknownFields
    0.75
    Activations Density 0.032%

    No Known Activations