© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14243
    Prev
    Next
    INDEX
    Explanations

    words ending in -ate, -use, -ute, -min or starting with diff- related to spreading or distributing information or other resources

    oai_token-act-pair · gemini-2.0-flash

    Technical documents, reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    Życiorys
    -0.54
    upuncture
    -0.51
     Porter
    -0.50
    válasz
    -0.50
    PORTER
    -0.50
     Chair
    -0.50
    bindValue
    -0.50
    MigrationBuilder
    -0.49
    Chair
    -0.49
    nungen
    -0.47
    POSITIVE LOGITS
     distribution
    0.99
     distributes
    0.96
     distributing
    0.93
     distribute
    0.91
     distribuzione
    0.89
     dissemination
    0.87
     distribuição
    0.86
    distribution
    0.85
     Distribution
    0.85
     spread
    0.83
    Activations Density 1.051%

    No Known Activations