© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12596
    Prev
    Next
    INDEX
    Explanations

    the word "both" and phrases that use "both" to indicate the presence of multiple elements

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the word 'both'

    np_token-act-pair-logits · gpt-4o-mini

    both

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     épaules
    -0.87
     touristes
    -0.86
     négociations
    -0.84
     vœux
    -0.81
     dieux
    -0.79
     lèvres
    -0.78
     bénéfices
    -0.77
     autorités
    -0.73
     investissements
    -0.73
     attentes
    -0.73
    POSITIVE LOGITS
     schemes
    0.78
     of
    0.76
     programs
    0.75
     accounts
    0.71
     sections
    0.70
     areas
    0.69
     cases
    0.69
     paths
    0.68
     routes
    0.68
     scenarios
    0.67
    Activations Density 2.202%

    No Known Activations