© 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. 2219
    Prev
    Next
    INDEX
    Explanations

    content related to Brazilian politics and corruption scandals

    oai_token-act-pair · gemini-2.0-flash

    Brazilian political scandals

    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
     Brazilian
    -1.52
     Brazil
    -1.44
     Argentine
    -1.41
    Brazilian
    -1.37
     Argent
    -1.31
     Argentina
    -1.30
     brazilian
    -1.28
    Brazil
    -1.27
     Peruvian
    -1.23
     Chilean
    -1.20
    POSITIVE LOGITS
     بيها
    0.60
    ColumnHeaders
    0.52
    IsContent
    0.48
     الحره
    0.47
    ächtig
    0.45
    portál
    0.45
    WarningLevel
    0.45
    الإنجليزية
    0.45
    ReadByte
    0.44
    CodedInputStream
    0.44
    Activations Density 0.939%

    No Known Activations