© 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. 13583
    Prev
    Next
    INDEX
    Explanations

    references to figures, tables, footnotes, and page numbers

    oai_token-act-pair · gemini-2.0-flash

    numbers

    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
     Мексичка
    -0.77
    ingeki
    -0.74
    nloa
    -0.69
     BorderRadius
    -0.61
    astéro
    -0.60
    transQ
    -0.56
     Phaser
    -0.55
    XmlType
    -0.54
    ={`/
    -0.52
    ِّف
    -0.51
    POSITIVE LOGITS
    ViewFeatures
    0.49
     Vordergrund
    0.49
    -
    0.48
    ,
    0.45
    зде
    0.40
     изд
    0.40
     poter
    0.40
    WAUKEE
    0.40
    modelBuilder
    0.39
    newArrayList
    0.39
    Activations Density 12.370%

    No Known Activations