© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8500
    Prev
    Next
    INDEX
    Explanations

    tokens that relate different concepts

    oai_token-act-pair · gemini-2.0-flash

    with and to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     rhestr
    -0.67
    ثيق
    -0.66
    soort
    -0.65
    AutoScaleMode
    -0.62
     FishBase
    -0.61
     EconPapers
    -0.60
    følgelig
    -0.59
     ISNI
    -0.57
    iseries
    -0.57
     Bacteriol
    -0.57
    POSITIVE LOGITS
    autoreleasepool
    0.54
     GenerationType
    0.52
     незавершена
    0.50
     Meksiku
    0.49
     AssemblyTitle
    0.49
    Portale
    0.48
    ModelAdmin
    0.48
    gelöst
    0.47
    gdx
    0.47
     Lordship
    0.46
    Activations Density 1.576%

    No Known Activations