© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 241918
    Prev
    Next
    INDEX
    Explanations

    unexpected meaning shifts

    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_25_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     আরও
    0.39
    四年
    0.35
    pointe
    0.35
    もっと
    0.34
    Джо
    0.34
    bidden
    0.34
    жнее
    0.34
    ر
    0.34
    μένος
    0.33
    нного
    0.33
    POSITIVE LOGITS
     malgré
    0.46
    मार्ग
    0.43
     ܒ
    0.41
    mediately
    0.40
     directamente
    0.40
     mesures
    0.40
     ຫຼື
    0.39
     facie
    0.38
     abon
    0.38
     merkez
    0.38
    Activations Density 0.004%

    No Known Activations