© 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. 1592
    Prev
    Next
    INDEX
    Explanations

    instances of something being transferred, given or passed on

    oai_token-act-pair · gemini-2.0-flash

    technical terms and functions

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

    Prepositions

    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
    nefs
    -0.74
    writeFieldEnd
    -0.73
    Manbalar
    -0.72
     resourceCulture
    -0.71
     Passes
    -0.69
     passes
    -0.68
     Passage
    -0.68
     Passed
    -0.66
    پیوند
    -0.66
     pass
    -0.66
    POSITIVE LOGITS
    RegressionTest
    0.63
    function
    0.43
     litri
    0.35
     الرخصة
    0.35
    linearGradient
    0.34
     것을
    0.33
    ι
    0.33
    タイトル
    0.33
    lahan
    0.33
    hankelijk
    0.33
    Activations Density 6.329%

    No Known Activations