© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9504
    Prev
    Next
    INDEX
    Explanations

    a mix of code, math and legal-sounding words.

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ЛЯ
    -0.56
     שוליים
    -0.56
    rentiel
    -0.55
    bewah
    -0.54
    AUD
    -0.53
    lutning
    -0.53
    kelijk
    -0.52
    pexpr
    -0.52
    ILLES
    -0.51
    ntlet
    -0.51
    POSITIVE LOGITS
     насељу
    0.85
     ExecuteAsync
    0.83
    ✨:
    0.62
     виправивши
    0.60
    Personendaten
    0.59
    انيف
    0.56
    )++;
    0.54
    Portale
    0.54
     indisponible
    0.54
    tagHelperRunner
    0.51
    Activations Density 5.615%

    No Known Activations