© 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. 7838
    Prev
    Next
    INDEX
    Explanations

    proper nouns associated with place names and people's names containing the letter sequence ber, am, or ans

    oai_token-act-pair · 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
    Negative Logits
    شهاد
    -0.52
    局
    -0.48
     staff
    -0.46
    stahl
    -0.46
    حياتها
    -0.45
     device
    -0.45
    xane
    -0.45
     ét
    -0.45
    atillo
    -0.45
     Gef
    -0.44
    POSITIVE LOGITS
    SpringBootTest
    0.81
    存于互联网档案馆
    0.77
     بيها
    0.71
    afficheront
    0.70
    verwijspagina
    0.69
    featureID
    0.63
     chests
    0.62
     niyang
    0.62
    ollectionView
    0.59
     juſ
    0.59
    Activations Density 0.986%

    No Known Activations