© 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. 6071
    Prev
    Next
    INDEX
    Explanations

    words related to church architecture and construction materials

    oai_token-act-pair · gemini-2.0-flash

    architecture descriptions

    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
    UserScript
    -0.77
    awtextra
    -0.72
    GEBURTSDATUM
    -0.71
    mybatisplus
    -0.69
     للمعارف
    -0.68
    Искәрмәләр
    -0.62
    tableFuture
    -0.62
    évaluateur
    -0.60
     FishBase
    -0.59
     Opis
    -0.59
    POSITIVE LOGITS
    bed
    0.48
    ിച്ച
    0.46
     Bed
    0.45
    GeneratedCode
    0.44
    ември
    0.44
     pageContext
    0.44
     mo
    0.43
    fileInfo
    0.42
    belli
    0.42
     g
    0.41
    Activations Density 0.326%

    No Known Activations