© 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. 13117
    Prev
    Next
    INDEX
    Explanations

    names of places and restaurants, especially in Spain

    oai_token-act-pair · gemini-2.0-flash

    Spanish place names

    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
     chng
    -0.77
     تضيفلها
    -0.71
    WebVitals
    -0.68
    ConstraintMaker
    -0.67
    :✨
    -0.63
     crossorigin
    -0.61
    UnusedPrivate
    -0.60
     betweenstory
    -0.60
     للمعارف
    -0.58
     numerus
    -0.58
    POSITIVE LOGITS
     Generale
    0.50
     catalana
    0.50
     comunale
    0.49
     Infantil
    0.48
     Sociale
    0.48
     humaine
    0.48
     blanches
    0.47
     rossa
    0.46
     umana
    0.46
     quæ
    0.46
    Activations Density 12.881%

    No Known Activations