© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16213
    Prev
    Next
    INDEX
    Explanations

    proper nouns and locations, especially of people and places specializing in East Asian descent

    oai_token-act-pair · gemini-2.0-flash

    Chinese 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
    AccessorTable
    -0.64
    UnusedPrivate
    -0.59
    RectangleBorder
    -0.57
     betweenstory
    -0.52
    IVEREF
    -0.50
    DoubleQuotes
    -0.49
    fromnode
    -0.46
     Roskov
    -0.46
    TagMode
    -0.44
    AnchorTagHelper
    -0.44
    POSITIVE LOGITS
     Kuan
    0.60
     Hua
    0.59
     Tung
    0.59
     Xiu
    0.58
     Soo
    0.58
    huan
    0.58
    uang
    0.58
     Chuan
    0.57
     Seng
    0.57
     Chai
    0.57
    Activations Density 14.268%

    No Known Activations