© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11527
    Prev
    Next
    INDEX
    Explanations

    the word "of" and some occurrences of "I", "on", "overtly", and "zy"

    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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     autorytatywna
    -0.57
    windowFixed
    -0.51
    ioutil
    -0.50
     RoutedEventArgs
    -0.49
    JspWriter
    -0.48
    wieś
    -0.48
    execSQL
    -0.47
     CreateTagHelper
    -0.47
    httphttps
    -0.47
    endcsname
    -0.47
    POSITIVE LOGITS
     course
    4.03
    course
    3.31
     Course
    3.02
     COURSE
    3.00
    Course
    2.83
    COURSE
    2.56
     courses
    2.42
     curso
    2.14
    courses
    2.05
     Courses
    2.02
    Activations Density 1.496%

    No Known Activations