© 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. 164813
    Prev
    Next
    INDEX
    Explanations

    example phrases

    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
     الطيب
    0.38
     przyjem
    0.37
    \}.
    0.36
    етесь
    0.35
    comodule
    0.35
     ஒதுக்க
    0.35
     hob
    0.34
    ுள்ள
    0.34
    ukam
    0.34
    ittee
    0.34
    POSITIVE LOGITS
     রেলস্ট
    0.42
    Scissors
    0.42
     leaderboard
    0.40
     vir
    0.39
     random
    0.38
    ൗ
    0.38
     transitive
    0.37
     diagonal
    0.37
     tears
    0.37
     emergency
    0.36
    Activations Density 0.065%

    No Known Activations