© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13668
    Prev
    Next
    INDEX
    Explanations

    words indicating a total number of instances of something, particularly legal offenses, medication dosages, or numerical totals

    oai_token-act-pair · gemini-2.0-flash

    counting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    
    -0.73
    +#+#
    -0.52
    يديا
    -0.52
    ([^
    -0.51
    !=-
    -0.49
    ereich
    -0.49
     choses
    -0.49
    ẫy
    -0.47
    tería
    -0.47
     estimés
    -0.47
    POSITIVE LOGITS
    setVerticalGroup
    0.77
     BoxDecoration
    0.74
    исленность
    0.71
    ArrowToggle
    0.62
    出版年
    0.62
    ValueStyle
    0.61
     Infórmanos
    0.60
    ContentAsync
    0.59
    HideFlags
    0.59
    protoc
    0.59
    Activations Density 1.541%

    No Known Activations