© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6193
    Prev
    Next
    INDEX
    Explanations

    a mix of code snippets and Portuguese words, particularly those related to political or bureaucratic events

    oai_token-act-pair · gemini-2.0-flash

    Brazilian politics

    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
    RenderAtEndOf
    -0.73
    SBATCH
    -0.72
    oredCriteria
    -0.70
    fjspx
    -0.70
    Rüyada
    -0.68
     Normdatei
    -0.67
     otomatig
    -0.67
     EconPapers
    -0.66
    SharedDtor
    -0.63
    ArrowToggle
    -0.62
    POSITIVE LOGITS
     cavalli
    0.57
     Pesquisa
    0.56
     légiti
    0.54
     aberto
    0.54
     aberta
    0.54
     legais
    0.53
     nacionais
    0.53
     internacionais
    0.52
     móvel
    0.52
     conhe
    0.51
    Activations Density 44.193%

    No Known Activations