© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7975
    Prev
    Next
    INDEX
    Explanations

    restaurant menu items and Malay language.

    oai_token-act-pair · gemini-2.0-flash

    indonesian/malay food and places

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     dan
    -0.73
    dan
    -0.54
    Dan
    -0.51
    Rüyada
    -0.50
    ones
    -0.50
     tant
    -0.50
     postIndex
    -0.49
     dal
    -0.47
     مص
    -0.46
    s
    -0.46
    POSITIVE LOGITS
    DropTable
    0.88
    ustimmung
    0.80
     AttributeSet
    0.80
     DriverManager
    0.80
    ándola
    0.79
     виправивши
    0.79
    RegistryLite
    0.79
     שוליים
    0.79
    ^(@)
    0.78
    DebuggerNonUser
    0.77
    Activations Density 0.059%

    No Known Activations