© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10019
    Prev
    Next
    INDEX
    Explanations

    mentions of time passing, including statements using "since" and the words "ever", "year", "decade"

    oai_token-act-pair · gemini-2.0-flash

    ever

    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
    Negative Logits
     néz
    -0.39
     đảo
    -0.37
    strcat
    -0.36
     desarrollado
    -0.36
     apellidos
    -0.35
    làm
    -0.34
    きた
    -0.34
    FontOfSize
    -0.34
    xia
    -0.33
     emot
    -0.33
    POSITIVE LOGITS
     ever
    3.66
    ever
    2.91
    Ever
    2.86
     Ever
    2.83
     EVER
    2.75
    EVER
    2.45
     jamais
    1.48
     jemals
    1.45
     ooit
    1.43
     evermore
    1.38
    Activations Density 1.650%

    No Known Activations