© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132007
    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_6_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
    자
    1.07
    á
    1.03
    제
    1.03
    اب
    0.94
    ف
    0.91
    あ
    0.91
    Р
    0.89
    ação
    0.88
    \%
    0.88
    た
    0.88
    POSITIVE LOGITS
     tilapia
    0.98
     chevron
    0.90
     slay
    0.86
     goldfish
    0.84
     springboard
    0.83
     he
    0.82
     faucet
    0.82
     commotion
    0.82
     bait
    0.81
     skillet
    0.80
    Activations Density 0.000%

    No Known Activations