© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11072
    Prev
    Next
    INDEX
    Explanations

    references to a piece of software called "Dextr"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    niająca
    -0.54
     EconPapers
    -0.52
    enumii
    -0.50
    Personensuche
    -0.49
    SequentialGroup
    -0.48
    bootstrapcdn
    -0.47
    Personendaten
    -0.47
     Exacts
    -0.44
    FormTagHelper
    -0.44
    RectangleBorder
    -0.42
    POSITIVE LOGITS
    
    0.72
     is
    0.71
     AssemblyTitle
    0.68
    gants
    0.66
    zusch
    0.66
    ROGEN
    0.64
    łecz
    0.63
     perfons
    0.62
     fans
    0.61
     does
    0.59
    Activations Density 9.343%

    No Known Activations