© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2881
    Prev
    Next
    INDEX
    Explanations

    Python code related to Django database models

    oai_token-act-pair · gemini-2.0-flash

    Code/technical snippets

    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
    Negative Logits
    ANGO
    -0.59
    createCanvas
    -0.57
    MENAFN
    -0.56
     ApiException
    -0.56
     pytest
    -0.56
    centralwidget
    -0.55
    ksikon
    -0.55
     draw
    -0.55
     estekak
    -0.54
    mbers
    -0.52
    POSITIVE LOGITS
    bootstrapcdn
    0.56
     legais
    0.50
     становника
    0.47
     };
    0.47
    NullException
    0.46
     wireType
    0.45
     bağlantılar
    0.45
    AnchorStyles
    0.44
    fromnode
    0.44
    blank
    0.44
    Activations Density 0.470%

    No Known Activations