© 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. 4811
    Prev
    Next
    INDEX
    Explanations

    references to time periods, especially centuries and ordinal numbers.

    oai_token-act-pair · gemini-2.0-flash

    say "century"

    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
     century
    -1.02
     Century
    -0.97
    Century
    -0.91
    century
    -0.88
     CENTURY
    -0.83
     millennium
    -0.69
    MessageOf
    -0.69
     siècle
    -0.60
     Jahrhundert
    -0.60
     siglo
    -0.59
    POSITIVE LOGITS
    itinéraire
    0.69
    uxxxx
    0.66
    DockStyle
    0.59
    ázaro
    0.56
     Audiodateien
    0.55
    Còn
    0.52
     itſelf
    0.52
    MLLoader
    0.50
    IsContent
    0.50
    Carriera
    0.50
    Activations Density 1.826%

    No Known Activations