© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 113425
    Prev
    Next
    INDEX
    Explanations

    un + noun

    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_2_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
    ни
    1.20
     un
    1.19
    کي
    1.12
     تاريخ
    1.02
     has
    1.00
    اسية
    1.00
    ťaž
    1.00
     一
    0.99
     championed
    0.99
     monstros
    0.97
    POSITIVE LOGITS
    you
    1.41
    I
    1.35
    は
    1.34
    เป็น
    1.33
    ات
    1.27
    t
    1.23
    P
    1.22
    きた
    1.21
    }
    1.21
    Y
    1.13
    Activations Density 0.001%

    No Known Activations