© 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. 200994
    Prev
    Next
    INDEX
    Explanations

    multi-lingual content

    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
    Not in Any Lists

    No Comments

    Negative Logits
     modulated
    0.41
    GJ
    0.39
     gond
    0.39
    GOR
    0.39
     ---
    0.38
     prevalence
    0.37
     Shiv
    0.37
     উচ্চার
    0.37
    Cô
    0.37
     नांदेड
    0.37
    POSITIVE LOGITS
    uldade
    0.43
    枼
    0.40
    ieke
    0.39
    ركة
    0.39
    matory
    0.38
    藻
    0.38
    ারি
    0.37
     LayoutInflater
    0.37
    òa
    0.37
    VISA
    0.37
    Activations Density 0.007%

    No Known Activations