© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 137354
    Prev
    Next
    INDEX
    Explanations

    4

    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_46_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
     الواحد
    0.41
     الواحده
    0.39
    驴
    0.38
     fourteen
    0.38
     Fourteen
    0.37
     четвер
    0.37
     چهار
    0.37
     nineteen
    0.36
     maturation
    0.35
    שור
    0.35
    POSITIVE LOGITS
    舸
    0.44
     kaps
    0.41
    Scenic
    0.39
     menggel
    0.39
    arga
    0.38
     Scenic
    0.38
    ops
    0.37
    ørte
    0.37
    boss
    0.37
    spend
    0.37
    Activations Density 0.015%

    No Known Activations