© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 200024
    Prev
    Next
    INDEX
    Explanations

    numbers and lists after them

    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_15_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
     современном
    0.52
     скры
    0.52
    III
    0.51
    د
    0.50
     современного
    0.48
    ፫
    0.48
    Who
    0.47
    Written
    0.46
    Coupon
    0.46
    Does
    0.46
    POSITIVE LOGITS
    ো
    0.54
     Up
    0.50
     Während
    0.49
    </code>
    0.48
     ton
    0.47
     CITY
    0.47
    <0x0D>
    0.47
     Baptism
    0.47
     Ton
    0.47
    ಂಟು
    0.47
    Activations Density 0.000%

    No Known Activations