© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5059
    Prev
    Next
    INDEX
    Explanations

    words related to Cuba, especially Havana, including tourism, culture, and the past

    oai_token-act-pair · gemini-2.0-flash

    geopolitics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Cuban
    -0.85
     Cuba
    -0.85
     CreateTagHelper
    -0.80
     Cubans
    -0.79
     cuban
    -0.78
    Cuba
    -0.75
    XmlAccessorType
    -0.74
     cubanos
    -0.73
    Cuban
    -0.73
    bootstrapcdn
    -0.72
    POSITIVE LOGITS
    Vidi
    0.41
     рас
    0.40
     Che
    0.40
     variabel
    0.39
     博
    0.38
     Sache
    0.38
    attach
    0.37
     inden
    0.36
    Che
    0.35
     DIG
    0.35
    Activations Density 1.774%

    No Known Activations