© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15971
    Prev
    Next
    INDEX
    Explanations

    a variety of words and phrases related to authors, books, and publishing, especially those by or about the author "Angela".

    oai_token-act-pair · gemini-2.0-flash

    Random text fragments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    UrlResolution
    -0.66
    SharedDtor
    -0.64
    #+#
    -0.63
    脚注の使い方
    -0.62
     DBNull
    -0.60
    Portale
    -0.57
     &___
    -0.56
    PerformLayout
    -0.56
    RegistryLite
    -0.55
     <=",
    -0.54
    POSITIVE LOGITS
     démocr
    0.54
     Pearls
    0.51
     ویکی‌پدیا
    0.51
     financières
    0.48
    šn
    0.47
     tromper
    0.47
     Sons
    0.47
     chré
    0.47
     Owls
    0.47
     Foxes
    0.46
    Activations Density 6.454%

    No Known Activations