© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12027
    Prev
    Next
    INDEX
    Explanations

    code snippets with specific formatting and keywords like `{@code`, `<pre>`, `<p>`, and `Ref<`

    oai_token-act-pair · gemini-2.0-flash

    source code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Kuru
    -0.69
    tinyos
    -0.69
    ainville
    -0.69
     Theodo
    -0.68
    expandindo
    -0.65
     Kongo
    -0.63
     Enfin
    -0.62
     Trondheim
    -0.61
     Chio
    -0.61
     Vex
    -0.60
    POSITIVE LOGITS
    PerformLayout
    0.87
     nakalista
    0.80
    InjectAttribute
    0.75
    ftagPool
    0.69
    下载附件
    0.68
     públicas
    0.63
    EndContext
    0.59
    GEBURTSDATUM
    0.59
     ***!
    0.58
    WriteTagHelper
    0.57
    Activations Density 1.763%

    No Known Activations