© 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. 5534
    Prev
    Next
    INDEX
    Explanations

    French places, especially cities in France, and opera houses

    oai_token-act-pair · gemini-2.0-flash

    European places

    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
     تضيفلها
    -0.77
    AndEndTag
    -0.65
     BoxDecoration
    -0.60
    PreferredItem
    -0.60
    SuppressMessage
    -0.60
     FetchType
    -0.60
    ագրություններ
    -0.59
    mybatisplus
    -0.57
    intios
    -0.55
    zzar
    -0.55
    POSITIVE LOGITS
     Barcelone
    0.63
     Limoges
    0.57
     Bourgogne
    0.57
     Liège
    0.56
     Poitiers
    0.56
     Amiens
    0.55
     Namur
    0.54
     Vichy
    0.53
     Viena
    0.53
     Maastricht
    0.53
    Activations Density 0.859%

    No Known Activations