© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12455
    Prev
    Next
    INDEX
    Explanations

    this neuron finds place names in China, and words related to medicine

    oai_token-act-pair · gemini-2.0-flash

    Locations and medicine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    twimg
    -0.55
    NameInMap
    -0.50
    InstrumentedTest
    -0.45
    ItemGroup
    -0.42
     ervan
    -0.41
    q
    -0.40
    v
    -0.40
    thren
    -0.40
     programmes
    -0.40
     против
    -0.39
    POSITIVE LOGITS
    存于互联网档案馆
    0.72
    DockStyle
    0.64
    GEBURTS
    0.61
    //</
    0.60
     CURIAM
    0.59
     ModelExpression
    0.59
    édrale
    0.58
    dawnictwo
    0.57
    findpost
    0.56
     WQS
    0.56
    Activations Density 1.244%

    No Known Activations