© 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. 235592
    Prev
    Next
    INDEX
    Explanations

    medium or intermediate level

    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
    Negative Logits
    €”
    0.39
    UTTON
    0.38
    ictures
    0.34
    ুখে
    0.34
     Ziele
    0.34
    르면
    0.34
     ডেইলি
    0.34
    延续
    0.34
    权利
    0.33
    Xinhua
    0.33
    POSITIVE LOGITS
     Beverage
    0.39
     プ
    0.38
    ម៉
    0.38
     aqui
    0.37
     لك
    0.37
    悝
    0.36
     légèrement
    0.35
     પર
    0.35
     podem
    0.35
     tarafından
    0.35
    Activations Density 0.007%

    No Known Activations