© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 83279
    Prev
    Next
    INDEX
    Explanations

    Black BlackBerry

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
     ALLO
    0.43
    طقة
    0.41
    )}^
    0.40
     Hewitt
    0.39
    HTT
    0.39
     Aly
    0.38
    ▬
    0.38
    ﾖ
    0.38
     Math
    0.37
     Союз
    0.37
    POSITIVE LOGITS
     bub
    0.41
     Burs
    0.41
    Noto
    0.41
    Black
    0.40
     trab
    0.40
     Black
    0.38
     ब्लैक
    0.38
     Trab
    0.38
    upart
    0.38
     BlackBerry
    0.38
    Activations Density 0.014%

    No Known Activations