© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13384
    Prev
    Next
    INDEX
    Explanations

    periods, particularly when they are next to another period or are at the end of a sentence that contains numbers

    oai_token-act-pair · gemini-2.0-flash

    Ending punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    tvguidetime
    -0.59
    ProgressHUD
    -0.56
    enegal
    -0.54
    MessageState
    -0.52
    KommentareTeilen
    -0.52
    abetes
    -0.52
     viewDidLoad
    -0.51
    WithEmail
    -0.48
    NewLabel
    -0.48
    graphicx
    -0.48
    POSITIVE LOGITS
    <bos>
    2.14
    ↵↵
    1.07
     ویکی‌پدی
    0.75
     архивлан
    0.70
     betweenstory
    0.64
     Италијани
    0.63
    #
    0.62
     the
    0.62
    OGND
    0.62
    /*
    0.60
    Activations Density 2.941%

    No Known Activations