© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 40405
    Prev
    Next
    INDEX
    Explanations

    Russian language

    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_57_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
    悛
    0.40
    мії
    0.38
     πρό
    0.38
     mach
    0.37
     dignity
    0.37
    לק
    0.35
    泬
    0.35
     br
    0.35
     fond
    0.34
     trop
    0.34
    POSITIVE LOGITS
    alnya
    0.38
     Driver
    0.36
     Crane
    0.35
     Lit
    0.35
     Yel
    0.35
    nection
    0.35
    싱
    0.35
     Employee
    0.34
     ಪರಿ
    0.34
     tenant
    0.33
    Activations Density 0.009%

    No Known Activations