© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36670
    Prev
    Next
    INDEX
    Explanations

    wedding cake introductions

    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_31_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
     الجسم
    0.45
     Sainsbury
    0.41
     întâm
    0.41
     страхо
    0.41
     Ortega
    0.40
     discontinu
    0.39
     intraven
    0.38
    昀
    0.38
     televisi
    0.37
    當時
    0.36
    POSITIVE LOGITS
    atter
    0.39
     REST
    0.38
     पान
    0.38
     mirrored
    0.38
    晶
    0.36
     пары
    0.34
     Pa
    0.33
    cakes
    0.33
    Fully
    0.33
    ueda
    0.33
    Activations Density 0.021%

    No Known Activations