© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 931
    Prev
    Next
    INDEX
    Explanations

    术后, 展会, 茶海, 视疲劳, 数学, 眼睛, 路 entry, water entry

    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_39_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
     Purchaser
    0.44
     alloying
    0.42
     शता
    0.41
     marketplaces
    0.40
    tiba
    0.40
    十七章
    0.40
    仃
    0.40
    衚
    0.40
     stoichi
    0.39
    र्यंत
    0.39
    POSITIVE LOGITS
    龄
    0.54
    齡
    0.52
    体的
    0.44
    况
    0.42
    齢
    0.42
    址
    0.39
    art
    0.38
     bliss
    0.38
    面に
    0.38
    blok
    0.37
    Activations Density 0.028%

    No Known Activations