© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4423
    Prev
    Next
    INDEX
    Explanations

    computer code

    oai_token-act-pair · gemini-2.0-flash

    Code drawing paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    jica
    -0.57
    basicConfig
    -0.56
     ویکی‌پدیا
    -0.51
    وأضاف
    -0.50
     Discre
    -0.47
    CommandText
    -0.46
     park
    -0.45
    LocalizedString
    -0.45
     Expan
    -0.44
     perv
    -0.44
    POSITIVE LOGITS
    出版年
    0.79
     beginnetje
    0.71
    IsMutable
    0.68
    
    0.61
    цезда
    0.55
    ItemBackground
    0.55
    Tembelea
    0.55
    agramm
    0.55
     незавершена
    0.54
    下载附件
    0.53
    Activations Density 2.301%

    No Known Activations