© 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. 14437
    Prev
    Next
    INDEX
    Explanations

    delimiters in legal and technical documents, especially periods following titles and numbers

    oai_token-act-pair · gemini-2.0-flash

    Periods

    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
    Negative Logits
    tvguidetime
    -1.10
    :✨
    -0.93
    NameInMap
    -0.78
    Datuak
    -0.77
     doInBackground
    -0.77
     resourceCulture
    -0.73
    Rüyada
    -0.72
    principalTable
    -0.72
    UnknownFieldSet
    -0.72
    DockStyle
    -0.71
    POSITIVE LOGITS
    Compan
    0.47
     should
    0.45
     @}
    0.44
    mask
    0.43
    oles
    0.42
     Rossi
    0.41
     masks
    0.40
    MANUEL
    0.40
    ứng
    0.39
     Masks
    0.39
    Activations Density 2.011%

    No Known Activations