© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13760
    Prev
    Next
    INDEX
    Explanations

    LaTeX mathematical notation

    oai_token-act-pair · gemini-2.0-flash

    Math notation characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    ScopeManager
    -0.67
    ↩
    -0.65
     وتسجيلات
    -0.60
    ReusableCell
    -0.59
    ucca
    -0.57
    Personendaten
    -0.57
    IDF
    -0.57
     configureStore
    -0.56
    danh
    -0.56
    chufe
    -0.55
    POSITIVE LOGITS
    <bos>
    1.44
    f
    0.60
    ValueStyle
    0.53
    if
    0.52
     חיצוניים
    0.48
    \
    0.48
    c
    0.48
     yağ
    0.48
    r
    0.47
     estimés
    0.47
    Activations Density 2.954%

    No Known Activations