© 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. 1268
    Prev
    Next
    INDEX
    Explanations

    words related to arranging meetings or fulfilling obligations

    oai_token-act-pair · gemini-2.0-flash

    schedule

    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
     schedule
    -2.41
    schedule
    -2.16
     Schedule
    -2.13
    Schedule
    -2.08
     schedules
    -2.02
     SCHEDULE
    -1.90
    SCHEDULE
    -1.83
     Schedules
    -1.72
     scheduling
    -1.65
     scheduled
    -1.59
    POSITIVE LOGITS
    ResponseWriter
    0.69
    GEBURTS
    0.68
    ViewFeatures
    0.63
    êques
    0.59
     inflam
    0.59
    براير
    0.59
     Smal
    0.58
    rature
    0.57
    orteur
    0.57
     ujednoznacz
    0.56
    Activations Density 11.882%

    No Known Activations