© 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. 14889
    Prev
    Next
    INDEX
    Explanations

    discourse about the Ustase regime in Croatia during World War II, particularly mentioning atrocities

    oai_token-act-pair · gemini-2.0-flash

    violence and death

    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
    ագրություններ
    -0.56
     الحره
    -0.54
    spesies
    -0.51
    ebbe
    -0.49
     OBB
    -0.48
    beginTransaction
    -0.47
    ъл
    -0.47
    
    -0.46
    Искәрмәләр
    -0.46
    ंदीखरीदारी
    -0.45
    POSITIVE LOGITS
    adpleegd
    0.66
    ScopeManager
    0.66
    ImageContext
    0.64
     StatelessWidget
    0.59
    twimg
    0.59
    unnitel
    0.58
    tagext
    0.56
     haters
    0.51
     africains
    0.51
     StatefulWidget
    0.49
    Activations Density 4.967%

    No Known Activations