© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4248
    Prev
    Next
    INDEX
    Explanations

    words related to trade and industry, especially in a supply chain context

    oai_token-act-pair · gemini-2.0-flash

    trade and products

    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
     items
    -0.88
     Items
    -0.81
     item
    -0.79
     Item
    -0.77
    Item
    -0.73
     ITEM
    -0.72
     goods
    -0.71
    items
    -0.67
     ITEMS
    -0.67
     Goods
    -0.66
    POSITIVE LOGITS
    StoryboardSegue
    0.73
    WithIOException
    0.71
    TagMode
    0.68
     onResponse
    0.68
    WireFormat
    0.61
     intptr
    0.59
    ftagPool
    0.56
     doInBackground
    0.56
    WillAppear
    0.54
    MemoryWarning
    0.52
    Activations Density 9.774%

    No Known Activations