© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35701
    Prev
    Next
    INDEX
    Explanations

    newspaper or publication names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enderita
    0.48
    ravel
    0.47
     It
    0.46
    voegd
    0.45
    ë
    0.45
    으로
    0.44
    0.44
     \\
    0.43
     நடந்து
    0.43
    yani
    0.43
    POSITIVE LOGITS
     newspaper
    0.75
    新聞
    0.68
    newspaper
    0.68
     newspapers
    0.66
     Newspapers
    0.65
    ဢ
    0.62
     Newspaper
    0.58
     newspap
    0.57
     அறிக்க
    0.56
    ʢ
    0.54
    Activations Density 0.010%

    No Known Activations