© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11719
    Prev
    Next
    INDEX
    Explanations

    words and phrases from a sales brochure for roofing tiles

    oai_token-act-pair · gemini-2.0-flash

    warranties or guarantees

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    HtmlAttribute
    -0.66
    ագրություններ
    -0.66
     كومونز
    -0.62
    tagHelperRunner
    -0.62
     Вікі
    -0.61
    ressible
    -0.60
    lanatory
    -0.59
     ujednoznacz
    -0.59
    iNdEx
    -0.56
    UnknownFields
    -0.54
    POSITIVE LOGITS
     lasting
    0.59
    lasting
    0.50
     uitz
    0.49
    弾
    0.46
    switch
    0.46
    Referenties
    0.45
    तिहास
    0.44
     Reverso
    0.44
     box
    0.44
     kekurangan
    0.43
    Activations Density 3.733%

    No Known Activations