© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1652
    Prev
    Next
    INDEX
    Explanations

    terms related to labor, cost, outsourcing, and historical economics

    oai_token-act-pair · gemini-2.0-flash

    Labor/Outsourcing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    <bos>
    -0.70
     Hivatalos
    -0.50
     División
    -0.47
     Mapping
    -0.47
    Mapping
    -0.46
     zákaz
    -0.45
    getSystem
    -0.45
     Metabolism
    -0.44
    Osp
    -0.44
     magnético
    -0.44
    POSITIVE LOGITS
    AddTagHelper
    0.71
    MigrationBuilder
    0.66
     Vikipedi
    0.64
    Varint
    0.63
    الحياه
    0.63
    XmlAccessType
    0.61
    URLException
    0.60
    ellular
    0.60
    ReusableCell
    0.59
     protoimpl
    0.58
    Activations Density 1.055%

    No Known Activations