© 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. 1551
    Prev
    Next
    INDEX
    Explanations

    uses of the word published and things related to releasing information.

    oai_token-act-pair · gemini-2.0-flash

    articles and numbers

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

    Articles, publications announcements

    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
    TintMode
    -0.77
     first
    -0.72
    first
    -0.71
    rrggbb
    -0.69
    First
    -0.66
    abord
    -0.62
    собенно
    -0.60
    ̍t
    -0.58
     First
    -0.58
     terbaik
    -0.55
    POSITIVE LOGITS
     a
    0.98
     another
    0.86
     an
    0.86
     CreateTagHelper
    0.65
    another
    0.64
     several
    0.62
     two
    0.59
     ſeveral
    0.59
     something
    0.59
     three
    0.56
    Activations Density 7.757%

    No Known Activations