© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13257
    Prev
    Next
    INDEX
    Explanations

    mentions of newspapers, time periods, places, and people, often found in news articles

    oai_token-act-pair · gemini-2.0-flash

    news and publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    cer
    -0.43
    v
    -0.43
    fe
    -0.43
    ↵↵
    -0.42
     quanto
    -0.41
     qu
    -0.41
     yıld
    -0.41
     
    -0.41
     Qu
    -0.41
    c
    -0.41
    POSITIVE LOGITS
     nakalista
    1.19
    parsedMessage
    1.09
     تضيفلها
    1.09
    الحياه
    1.08
     GeoNames
    1.07
    LookAnd
    1.05
     يتيمه
    1.02
    GEBURTSDATUM
    1.02
     Савезне
    1.00
    ьаж
    0.99
    Activations Density 0.737%

    No Known Activations