© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5262
    Prev
    Next
    INDEX
    Explanations

    dates and numbers in the first half of the 20th century

    oai_token-act-pair · gemini-2.0-flash

    say "Alternating 1 and 2"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     pleaſure
    -0.66
     ―――――
    -0.61
     raiſ
    -0.60
     myſelf
    -0.58
     Reſ
    -0.57
     itſelf
    -0.56
     Majefty
    -0.55
    ſelf
    -0.54
     ſta
    -0.53
     purpoſe
    -0.53
    POSITIVE LOGITS
    
    0.75
     be
    0.63
     vectorielles
    0.63
     undangan
    0.63
     in
    0.62
     graciosas
    0.61
     spéciaux
    0.61
     chimiques
    0.60
     étro
    0.60
     vectoriales
    0.59
    Activations Density 26.045%

    No Known Activations