Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14384
    Prev
    Next
    INDEX
    Explanations

    text related to political scandals, particularly in Brazil or Thailand, and especially about the act of overthrowing.

    oai_token-act-pair · gemini-2.0-flash

    Brazil 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_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    onAttach
    -0.48
    Alike
    -0.48
    WaitGroup
    -0.48
     Ortsteil
    -0.47
    ServletException
    -0.47
    
    -0.47
     bico
    -0.46
     Continent
    -0.45
    copyFrom
    -0.45
    ftagPool
    -0.45
    POSITIVE LOGITS
    StoryboardSegue
    0.58
    GHIJKLM
    0.53
    Opposition
    0.52
    Geplaatst
    0.51
     Privat
    0.51
     nawr
    0.51
    opposition
    0.50
     נת
    0.50
    alts
    0.49
    pointments
    0.49
    Activations Density 1.872%

    No Known Activations