© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15466
    Prev
    Next
    INDEX
    Explanations

    dates and formal language, likely in legal or official documents.

    oai_token-act-pair · gemini-2.0-flash

    calendar months and date-related terms

    np_token-act-pair-logits · gpt-4o-mini

    Months

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    tahui
    -0.54
    ();)
    -0.54
    存于互联网档案馆
    -0.53
    خول
    -0.53
    \{\\
    -0.52
    ற்க
    -0.51
    MessageTagHelper
    -0.50
    !*\
    -0.49
     Feste
    -0.49
     CreateTagHelper
    -0.49
    POSITIVE LOGITS
    EndGlobalSection
    0.55
     August
    0.53
    September
    0.52
     agosto
    0.52
    January
    0.51
     October
    0.51
    February
    0.51
    june
    0.50
     February
    0.50
     AssemblyCulture
    0.50
    Activations Density 8.852%

    No Known Activations