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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 776
    Prev
    Next
    INDEX
    Explanations

    words that refer to nations and their potential conflicts

    oai_token-act-pair · gemini-2.0-flash

    Political/historical contexts

    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
    expandindo
    -0.77
     mergeFrom
    -0.71
    Referències
    -0.62
    клопе
    -0.56
    Aiheesta
    -0.53
     урна
    -0.53
     relâche
    -0.52
    iParam
    -0.49
    IBOutlet
    -0.47
    lands
    -0.47
    POSITIVE LOGITS
    featureID
    0.67
     EconPapers
    0.61
    ]")]
    0.57
    reportWebVitals
    0.56
     under
    0.54
     Godhead
    0.52
     ſee
    0.49
     glaube
    0.48
    itename
    0.48
    Under
    0.48
    Activations Density 5.383%

    No Known Activations