© 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. 10342
    Prev
    Next
    INDEX
    Explanations

    interrogative words or phrases, like questions or uncertainties

    oai_token-act-pair · gemini-2.0-flash

    forum comments

    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
    MergeFrom
    -0.60
    rungsseite
    -0.57
    exitRule
    -0.56
    MigrationBuilder
    -0.55
    存于互联网档案馆
    -0.54
     MaterialApp
    -0.51
    homonymie
    -0.50
     Мексичка
    -0.50
    osť
    -0.49
    anmoins
    -0.49
    POSITIVE LOGITS
    Autoritní
    0.70
    ↵↵
    0.56
     monoch
    0.48
     call
    0.46
     Keychain
    0.46
     kịch
    0.45
    javas
    0.45
    шные
    0.45
     roue
    0.45
    copyWith
    0.44
    Activations Density 1.610%

    No Known Activations