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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11292
    Prev
    Next
    INDEX
    Explanations

    names of countries, cities, or regions

    oai_token-act-pair · gemini-2.0-flash

    places

    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
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.61
     fieldNum
    -0.57
    hören
    -0.54
    ніципа
    -0.53
    บัติ
    -0.52
    fromnode
    -0.50
     Spade
    -0.48
     aimez
    -0.48
     commerciaux
    -0.48
    éras
    -0.47
    POSITIVE LOGITS
     raiſ
    0.80
     ſever
    0.78
     myſelf
    0.76
     ſta
    0.74
     uſed
    0.73
     faſt
    0.71
     deſt
    0.71
     juſ
    0.69
     perſon
    0.68
     ſhe
    0.68
    Activations Density 1.320%

    No Known Activations