© 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. 9521
    Prev
    Next
    INDEX
    Explanations

    news sources and people involved in journalism

    oai_token-act-pair · gemini-2.0-flash

    news and journalism

    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
     reporter
    -0.73
     Correspondent
    -0.69
    ValueStyle
    -0.69
     journalist
    -0.69
     correspondent
    -0.68
     journalists
    -0.67
     journaliste
    -0.66
     journalistic
    -0.65
     Journalism
    -0.65
     wartawan
    -0.64
    POSITIVE LOGITS
     actionMode
    0.56
    !(:
    0.50
    fassung
    0.50
    MEMORANDUM
    0.49
    φι
    0.49
    CloseOperation
    0.48
    ontas
    0.48
     attendance
    0.47
     #:
    0.46
    ี่ยน
    0.46
    Activations Density 0.369%

    No Known Activations