© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10285
    Prev
    Next
    INDEX
    Explanations

    the expressions "one day" or "one * day" (where * is any token)

    oai_token-act-pair · gemini-2.0-flash

    day

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     stabilisation
    -0.54
     annealed
    -0.52
     sobbed
    -0.50
     ceb
    -0.49
     periodically
    -0.48
    CreateMap
    -0.48
     automaticamente
    -0.47
    Prima
    -0.47
     lowered
    -0.47
     underwent
    -0.46
    POSITIVE LOGITS
    EndContext
    0.64
     <>",
    0.62
     estekak
    0.62
    ⓧ
    0.61
     ран
    0.59
     early
    0.59
    Hentet
    0.59
     useAppContext
    0.58
     initComponents
    0.58
    SequentialGroup
    0.56
    Activations Density 0.485%

    No Known Activations