© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8231
    Prev
    Next
    INDEX
    Explanations

    punctuation or stop words like 'but' appearing in the middle of sentences or phrases

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Хьажоргаш
    -0.47
     Wiktionnaire
    -0.46
     spille
    -0.45
    TABLE
    -0.44
     vertes
    -0.43
    ISODE
    -0.43
     farine
    -0.42
    ыгана
    -0.42
     merely
    -0.41
     intensification
    -0.41
    POSITIVE LOGITS
    DebuggerNonUser
    0.73
    Referències
    0.67
    ConverterFactory
    0.61
     Bioaccumulative
    0.56
     onOptions
    0.55
    enoord
    0.55
    aarrggbb
    0.54
    jspx
    0.54
    djangoproject
    0.54
    FailureListener
    0.54
    Activations Density 2.549%

    No Known Activations