© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 96436
    Prev
    Next
    INDEX
    Explanations

    works of

    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_14_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
    itch
    0.57
    O
    0.57
    sti
    0.54
    nolds
    0.52
    Unlock
    0.51
    勰
    0.51
    imas
    0.50
    Take
    0.49
    sss
    0.49
    Aren
    0.49
    POSITIVE LOGITS
     niż
    0.63
     หลาย
    0.54
    getCQL
    0.54
     dispositivi
    0.53
     ใส่
    0.53
     ад
    0.52
    тів
    0.52
     медицин
    0.52
    ﺔ
    0.52
     conseiller
    0.51
    Activations Density 0.002%

    No Known Activations