© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12801
    Prev
    Next
    INDEX
    Explanations

    news articles about international current events, politics, or business deals

    oai_token-act-pair · gemini-2.0-flash

    News headlines and announcements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     שוליים
    -0.62
     clairement
    -0.60
     bezeichneter
    -0.59
    ImageContext
    -0.58
     Sơ
    -0.58
    clearly
    -0.57
     represen
    -0.56
    ństw
    -0.55
    StreetMap
    -0.54
     Parenthood
    -0.52
    POSITIVE LOGITS
     doPost
    0.70
     Ans
    0.55
     ans
    0.54
    ange
    0.47
    BOU
    0.47
    modelBuilder
    0.45
    ädie
    0.45
     ویکی‌پدی
    0.45
     catch
    0.45
    Ans
    0.45
    Activations Density 8.035%

    No Known Activations