© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3966
    Prev
    Next
    INDEX
    Explanations

    planning and setup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_39_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
     Meek
    0.37
     Mikro
    0.36
     যারা
    0.36
     ইউনিভার্সিটি
    0.36
    intel
    0.35
     स्की
    0.35
     जिसने
    0.34
    ～。
    0.34
    ﻮ
    0.34
    
    0.34
    POSITIVE LOGITS
     ceremonia
    0.43
     पंड
    0.41
     পয়
    0.41
     cerim
    0.41
    之处
    0.38
     cérémonie
    0.38
     द्विवेदी
    0.37
    frey
    0.37
    лади
    0.37
     excellence
    0.36
    Activations Density 0.141%

    No Known Activations