© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 194628
    Prev
    Next
    INDEX
    Explanations

    George

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    providers
    0.43
    யோ
    0.37
    ㅆ
    0.37
    ضب
    0.37
    bled
    0.37
     оцен
    0.37
     MUN
    0.37
    bians
    0.37
    Providers
    0.36
     Pach
    0.36
    POSITIVE LOGITS
     george
    0.40
    ificacion
    0.38
    тона
    0.38
    Durch
    0.37
    슬
    0.36
     ин
    0.36
    George
    0.36
    しくは
    0.36
     gill
    0.35
     George
    0.35
    Activations Density 0.003%

    No Known Activations