© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3775
    Prev
    Next
    INDEX
    Explanations

    numerical ID's and urls

    oai_token-act-pair · gemini-2.0-flash

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     ainfi
    -0.91
     myſelf
    -0.91
     greateſt
    -0.91
     itſelf
    -0.90
     pleaſure
    -0.84
     ſeveral
    -0.83
     himſelf
    -0.83
     Monfieur
    -0.83
     métallique
    -0.81
     ब्रेकडाउन
    -0.81
    POSITIVE LOGITS
     digital
    0.55
    .
    0.52
     "
    0.48
     The
    0.46
    :
    0.45
     :
    0.45
     Digital
    0.45
    …
    0.43
     As
    0.43
    ↵↵
    0.43
    Activations Density 0.993%

    No Known Activations