© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54825
    Prev
    Next
    INDEX
    Explanations

    new Java/Forms object creation

    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_30_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
    ioi
    0.29
    甘
    0.29
     Kep
    0.29
     slits
    0.28
    zij
    0.28
    Kep
    0.28
    dze
    0.28
     dinam
    0.26
    Translatef
    0.26
    Infos
    0.26
    POSITIVE LOGITS
     প্রচেষ্টা
    0.26
    誂
    0.25
     क्लिक
    0.25
     SIP
    0.25
     EDA
    0.25
    ედა
    0.24
     Pikachu
    0.24
     তীরে
    0.24
    娅
    0.24
     কাজে
    0.24
    Activations Density 0.004%

    No Known Activations