© 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. 194677
    Prev
    Next
    INDEX
    Explanations

    fanfiction

    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
     করিল
    0.43
    __.__
    0.40
    ギン
    0.39
    iqui
    0.38
    ၈
    0.37
     Jalisco
    0.37
    annulation
    0.37
    漏洞
    0.36
    Claire
    0.36
    濩
    0.36
    POSITIVE LOGITS
     FI
    1.44
     фи
    1.39
     фі
    1.34
     Фи
    1.30
    Фи
    1.29
    FI
    1.28
     فی
    1.23
    フィ
    1.22
     Fi
    1.22
     Fib
    1.21
    Activations Density 0.000%

    No Known Activations