© 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. 175524
    Prev
    Next
    INDEX
    Explanations

    foreign languages

    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
    خي
    0.40
    ణ
    0.40
    ANI
    0.39
     Epistle
    0.38
    議
    0.38
    んど
    0.38
    先に
    0.38
    فك
    0.36
    ім
    0.36
     neoc
    0.36
    POSITIVE LOGITS
     Acc
    0.45
    Acc
    0.38
     Lad
    0.37
    Mor
    0.35
     पाल
    0.35
    ้องกัน
    0.35
     khám
    0.35
     Liberal
    0.35
     ويا
    0.35
    학교
    0.35
    Activations Density 0.000%

    No Known Activations