© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 100988
    Prev
    Next
    INDEX
    Explanations

    war, labor, SEC, Troubles

    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_14_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
    ություն
    0.62
     кроме
    0.53
    હ
    0.52
     дочери
    0.51
     Kirchhoff
    0.51
     রোহি
    0.50
     madde
    0.50
    壤
    0.50
     Украины
    0.50
     রোহিঙ্গাদের
    0.49
    POSITIVE LOGITS
     جائزہ
    0.52
     P
    0.48
    เภท
    0.46
     t
    0.44
    AGES
    0.44
    GPa
    0.43
     caric
    0.43
     Sanford
    0.43
     Newman
    0.42
    ġ
    0.42
    Activations Density 0.003%

    No Known Activations