© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13609
    Prev
    Next
    INDEX
    Explanations

    brand names and phrases mentioning a brand

    oai_token-act-pair · gemini-2.0-flash

    Reviews/Descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     providing
    -0.53
     Offering
    -0.53
     serving
    -0.53
     offering
    -0.52
     Providing
    -0.50
    providing
    -0.50
    יהם
    -0.50
    ()==
    -0.49
    offering
    -0.48
     Offered
    -0.48
    POSITIVE LOGITS
    RegistryLite
    0.85
    Vidite
    0.83
     cherchés
    0.79
    verwijspagina
    0.77
    ParallelGroup
    0.77
    NameInMap
    0.76
    SourceChecksum
    0.73
     فريبيس
    0.73
     CreateTagHelper
    0.71
     Bioaccumulative
    0.71
    Activations Density 1.242%

    No Known Activations