© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14941
    Prev
    Next
    INDEX
    Explanations

    .NET Framework

    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_13_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
    erio
    0.44
     dogged
    0.44
     claimed
    0.41
     {
    0.40
     attempted
    0.39
     dreamed
    0.38
    perd
    0.38
     soiled
    0.37
     cheaper
    0.37
     GRAND
    0.37
    POSITIVE LOGITS
     সমৃদ্ধ
    0.37
    ណៈ
    0.36
    ﻲ
    0.35
    equals
    0.34
     offsetX
    0.34
    หนึ่ง
    0.32
     unital
    0.32
     USART
    0.32
    為了
    0.31
     ব্রাহ্মণ
    0.31
    Activations Density 0.020%

    No Known Activations