© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7479
    Prev
    Next
    INDEX
    Explanations

    the phrase "from time to time"

    oai_token-act-pair · gemini-2.0-flash

    words involving time and frequency

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

    time

    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
     now
    -1.45
    now
    -1.23
     Now
    -1.17
    Now
    -1.17
     maintenant
    -0.96
     NOW
    -0.94
     ahora
    -0.94
    NOW
    -0.94
     теперь
    -0.90
     désormais
    -0.85
    POSITIVE LOGITS
     Efq
    0.80
     Monfieur
    0.77
    ſelves
    0.75
     greateſt
    0.75
    soever
    0.74
     myſelf
    0.73
    ſelf
    0.72
     ་་
    0.72
     purpoſe
    0.71
     Shakspeare
    0.69
    Activations Density 0.090%

    No Known Activations