© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27406
    Prev
    Next
    INDEX
    Explanations

    initials and abbreviations

    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_10_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
     can
    0.23
     Dungeon
    0.22
     for
    0.21
    把
    0.20
    點
    0.20
     edilen
    0.20
     don
    0.20
     centaines
    0.20
     $
    0.20
    िश्चित
    0.19
    POSITIVE LOGITS
    (
    0.22
    aye
    0.18
    ie
    0.18
    speople
    0.17
    م
    0.17
    0
    0.17
    ivano
    0.17
    र्द
    0.16
    creativecommons
    0.16
     wakati
    0.16
    Activations Density 0.004%

    No Known Activations