© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10353
    Prev
    Next
    INDEX
    Explanations

    xml and code

    oai_token-act-pair · gemini-2.0-flash

    Code/programming terms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ↵↵
    -0.97
    ↵
    -0.75
    ↵↵↵
    -0.58
     $
    -0.55
    lak
    -0.52
    ↵↵↵↵
    -0.48
     A
    -0.48
     
    -0.48
     “
    -0.47
    la
    -0.47
    POSITIVE LOGITS
     للاسماء
    1.05
    DockStyle
    0.94
    InputBorder
    0.90
    ValueStyle
    0.86
     '\\;'
    0.79
    GEBURTSDATUM
    0.79
     bezeichneter
    0.79
     **/
    0.74
    TagMode
    0.73
    ErrUnexpectedEOF
    0.71
    Activations Density 1.713%

    No Known Activations