© 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. 4395
    Prev
    Next
    INDEX
    Explanations

    scientific and technical writing related to quantum physics, particularly X-ray spectroscopy, dynamics, and quantum dots.

    oai_token-act-pair · gemini-2.0-flash

    experimental studies

    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
    principalTable
    -0.66
    RetentionPolicy
    -0.54
    хьтан
    -0.49
     JsonConvert
    -0.48
    fxml
    -0.47
    deld
    -0.46
     integrate
    -0.45
    parsedMessage
    -0.44
     integration
    -0.43
     Integrating
    -0.43
    POSITIVE LOGITS
     Majefty
    0.74
     Houſe
    0.73
     Efq
    0.68
     houſe
    0.68
     greateſt
    0.64
     NSCoder
    0.63
    sizeCache
    0.62
    省市镇
    0.60
     Anſ
    0.60
    はじめに
    0.59
    Activations Density 5.634%

    No Known Activations