© 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-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 220432
    Prev
    Next
    INDEX
    Explanations

    more difficult, powerful, accurate, satisfying

    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_10_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    на
    0.54
    وي
    0.49
    ه
    0.49
    يس
    0.48
    ير
    0.46
    سم
    0.44
    ايا
    0.43
    بي
    0.43
    ني
    0.42
    يا
    0.42
    POSITIVE LOGITS
    '
    0.43
    million
    0.43
     externalities
    0.41
    ated
    0.39
    methyl
    0.39
    HAND
    0.39
     Еўропы
    0.38
    Capstone
    0.38
    ballage
    0.38
     Lotion
    0.37
    Activations Density 0.005%

    No Known Activations