© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 198197
    Prev
    Next
    INDEX
    Explanations

    Lucy/Lucia

    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
     hir
    0.41
    锒
    0.40
     jeito
    0.37
    ഗോ
    0.37
    折扣
    0.37
    ゴ
    0.36
    不正
    0.36
     deg
    0.35
     cate
    0.35
    Bil
    0.35
    POSITIVE LOGITS
    svc
    0.40
    ષ
    0.40
    dienst
    0.39
    HSL
    0.39
     svc
    0.39
     Boyce
    0.39
     glyc
    0.38
    ostomy
    0.38
    Swipe
    0.37
    ﻘ
    0.37
    Activations Density 0.000%

    No Known Activations