© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7249
    Prev
    Next
    INDEX
    Explanations

    the word "of" or the phrase "of course"

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     course
    -1.05
    AccessorTable
    -0.94
     unknownFields
    -0.91
    course
    -0.90
     COURSE
    -0.88
     ProtoMessage
    -0.88
    OrBuilder
    -0.88
    Course
    -0.83
     Course
    -0.80
    脚注の使い方
    -0.80
    POSITIVE LOGITS
     most
    0.50
    co
    0.49
     Most
    0.48
    lc
    0.47
    unc
    0.46
     Corey
    0.46
     cor
    0.46
    xC
    0.46
     cause
    0.46
    cor
    0.46
    Activations Density 1.329%

    No Known Activations