© 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. 7585
    Prev
    Next
    INDEX
    Explanations

    API retrieval

    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
     عمليه
    0.42
     operazioni
    0.38
    Glasgow
    0.38
     operasi
    0.37
    锼
    0.37
     عمليات
    0.37
     операция
    0.36
     হোম
    0.36
     ফাইল
    0.36
     科
    0.35
    POSITIVE LOGITS
     reading
    0.41
     retrieves
    0.41
     retrieve
    0.40
     fetch
    0.40
    fetch
    0.39
     schedule
    0.39
    полу
    0.39
     resolve
    0.37
    Полу
    0.37
    posts
    0.37
    Activations Density 0.034%

    No Known Activations