© 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. 15264
    Prev
    Next
    INDEX
    Explanations

    non-English snippets within a document in a variety of languages, potentially identifying language changes or foreign language content

    oai_token-act-pair · gemini-2.0-flash

    special terms related to data or systems

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

    Facebook account creation

    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
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.52
    áját
    -0.52
    arXiv
    -0.41
    ‏‏
    -0.40
    يت
    -0.40
    ából
    -0.39
     Barat
    -0.39
    傍
    -0.39
    ãs
    -0.39
     kir
    -0.38
    POSITIVE LOGITS
    MigrationBuilder
    0.91
     pinulongan
    0.82
     utafitiHapana
    0.77
     supérieurs
    0.77
     démocr
    0.74
     spéciaux
    0.73
     صوتيه
    0.72
     communs
    0.71
    :✨
    0.71
     définiti
    0.70
    Activations Density 0.096%

    No Known Activations