© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9312
    Prev
    Next
    INDEX
    Explanations

    legal opinions, references to courts, government, the constitution, or jurisprudence

    oai_token-act-pair · gemini-2.0-flash

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    تقاوى
    -0.91
    :✨
    -0.90
    Personensuche
    -0.89
     незавершена
    -0.87
    expandindo
    -0.86
    contentLoaded
    -0.79
     Wikimedijinoj
    -0.75
    PreferredItem
    -0.74
    oredCriteria
    -0.73
     Италијани
    -0.72
    POSITIVE LOGITS
     ›
    0.49
    ített
    0.49
    NullException
    0.47
     поги
    0.47
     چون
    0.47
     vi
    0.47
     ning
    0.47
     защото
    0.47
    landi
    0.46
     ·
    0.46
    Activations Density 11.851%

    No Known Activations