© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3290
    Prev
    Next
    INDEX
    Explanations

    the word "Main," often in the context of locations or menus

    oai_token-act-pair · gemini-2.0-flash

    Main

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    er
    -0.71
    Item
    -0.68
    ed
    -0.66
    i
    -0.63
    es
    -0.63
    en
    -0.62
    ki
    -0.61
    y
    -0.61
    ia
    -0.59
    ar
    -0.58
    POSITIVE LOGITS
     дописавши
    1.37
    DockStyle
    1.34
    Tikang
    1.23
    RenderAtEndOf
    1.22
    contentLoaded
    1.22
    NameInMap
    1.21
    InputBorder
    1.19
    IndentedString
    1.18
     незавершена
    1.15
    invokeLater
    1.15
    Activations Density 0.841%

    No Known Activations