© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218468
    Prev
    Next
    INDEX
    Explanations

    contained herein

    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_31_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
    ested
    0.40
     ino
    0.39
    董事
    0.39
     microSD
    0.39
     strtotime
    0.39
     प्रव
    0.38
    ម្ម
    0.37
    异
    0.37
    แกรม
    0.37
    heter
    0.36
    POSITIVE LOGITS
     rispar
    0.43
    Cause
    0.41
     enthält
    0.41
     मस्त
    0.38
     Packages
    0.38
     contained
    0.37
     cause
    0.36
     Bans
    0.36
     Cause
    0.36
    Laws
    0.36
    Activations Density 0.000%

    No Known Activations