© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14078
    Prev
    Next
    INDEX
    Explanations

    references to the 20th and 21st centuries

    oai_token-act-pair · gemini-2.0-flash

    20th/21st-century topics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    2
    -1.27
    ２
    -0.98
     twenty
    -0.93
     Twenty
    -0.88
    ২
    -0.83
     ۲
    -0.82
    ۲
    -0.82
    twenty
    -0.81
    二十
    -0.80
     ٢
    -0.79
    POSITIVE LOGITS
     triple
    0.53
    moveToFirst
    0.53
    SharedCtor
    0.48
     ControllerBase
    0.48
     propOrder
    0.47
     Italijanski
    0.47
    InsertCommand
    0.46
     suerte
    0.46
    Хьажоргаш
    0.45
     quadruple
    0.45
    Activations Density 2.537%

    No Known Activations