© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261026
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_5_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
     an
    1.77
     be
    1.59
    you
    1.37
     you
    1.33
     can
    1.27
    م
    1.25
     a
    1.18
     to
    1.18
     it
    1.16
    ల
    1.16
    POSITIVE LOGITS
    3
    1.29
    0
    1.23
    и
    1.15
     eficiencia
    1.09
    вет
    1.06
    ﺭ
    1.03
    ﻭ
    1.00
    وں
    0.99
    는
    0.99
    ։
    0.99
    Activations Density 0.000%

    No Known Activations