© 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. 195386
    Prev
    Next
    INDEX
    Explanations

    writing

    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
    Negative Logits
    坦克
    0.37
    经销
    0.35
    演奏
    0.34
    ாய்ச்ச
    0.34
     {{-
    0.34
    Generate
    0.33
    क्लो
    0.32
    簍
    0.32
     erect
    0.32
     ऑर्
    0.32
    POSITIVE LOGITS
     write
    2.55
     writing
    2.47
     kirjo
    2.38
     Write
    2.36
    寫
    2.33
     menulis
    2.31
    write
    2.28
     escrever
    2.28
    写
    2.28
    Write
    2.25
    Activations Density 0.063%

    No Known Activations