© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 219542
    Prev
    Next
    INDEX
    Explanations

    Delta

    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_47_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
    ಿಕೆ
    0.43
    併
    0.41
    合并
    0.40
     Third
    0.40
     लो
    0.39
    iry
    0.38
    itaea
    0.38
    iret
    0.37
    ired
    0.36
     torch
    0.36
    POSITIVE LOGITS
    лювання
    0.40
     झालं
    0.40
    ટું
    0.38
    Cob
    0.38
    (:,:,
    0.37
     бумаги
    0.37
     буквы
    0.36
    пан
    0.36
    কবি
    0.36
    지에
    0.35
    Activations Density 0.000%

    No Known Activations