© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 90339
    Prev
    Next
    INDEX
    Explanations

    cicadas and wheat flour

    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_23_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
    𝐪
    0.44
    يبه
    0.43
    皙
    0.43
    期間
    0.41
    षिक
    0.41
     പ്രതിഷേധ
    0.40
     اداکار
    0.40
    ፆ
    0.40
    頹
    0.39
    𝐛
    0.39
    POSITIVE LOGITS
     Het
    0.44
    Ind
    0.44
    ão
    0.41
     TF
    0.41
     آن‌ها
    0.41
     They
    0.41
     W
    0.40
     G
    0.40
    !
    0.40
     We
    0.40
    Activations Density 0.000%

    No Known Activations