© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 228893
    Prev
    Next
    INDEX
    Explanations

    men's clothing

    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_6_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
    ل
    1.30
    א
    1.24
    л
    1.22
    ה
    1.18
    ת
    1.16
    ב
    1.16
    of
    1.15
    ל
    1.09
    т
    1.05
    其他
    1.05
    POSITIVE LOGITS
    arı
    0.97
     for
    0.88
     tại
    0.88
     і
    0.86
     ಅಧಿಕಾರಿ
    0.85
    sexual
    0.84
     profane
    0.84
    for
    0.83
    desc
    0.83
    weekday
    0.83
    Activations Density 0.001%

    No Known Activations