© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7817
    Prev
    Next
    INDEX
    Explanations

    occurrences of numerical data, chemical formulas, common scientific abbreviations, and citations to research papers.

    oai_token-act-pair · gemini-2.0-flash

    [@

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    <bos>
    -1.59
    Personendaten
    -0.98
     الرياضيه
    -0.95
     tartalomajánló
    -0.95
    StructEnd
    -0.91
    tagHelperRunner
    -0.88
    DockStyle
    -0.84
     Савезне
    -0.82
    ArrowToggle
    -0.81
     ویکی‌پدیا
    -0.79
    POSITIVE LOGITS
    </i>
    0.49
    nach
    0.48
     way
    0.46
    zeh
    0.46
    ment
    0.45
    ,
    0.45
    </u>
    0.45
     es
    0.44
    .
    0.44
    arre
    0.43
    Activations Density 23.776%

    No Known Activations