© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15134
    Prev
    Next
    INDEX
    Explanations

    news articles about Brazilian politics and corruption, especially those mentioning magazine names, place names, governmental roles, politicians, and financial transactions.

    oai_token-act-pair · gemini-2.0-flash

    Brazilian politics and media

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ImageContext
    -0.63
     defaultstate
    -0.61
    AnimationsModule
    -0.57
    Identyfik
    -0.57
     continúas
    -0.53
     wireType
    -0.53
    ParallelGroup
    -0.53
     autorytatywna
    -0.52
    WebMethod
    -0.52
     समीक्षाएं
    -0.52
    POSITIVE LOGITS
    ю
    1.15
    Ю
    0.57
    й
    0.55
     متعلقه
    0.52
     Toen
    0.51
     Dân
    0.50
     INSEE
    0.50
    ochim
    0.50
    transQ
    0.49
    ью
    0.49
    Activations Density 2.148%

    No Known Activations