© 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. 203598
    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
    ↵
    1.15
    ite
    1.09
    una
    1.00
    up
    0.99
    ও
    0.98
    ate
    0.96
    oc
    0.96
    ob
    0.95
     in
    0.94
    ot
    0.93
    POSITIVE LOGITS
    것
    1.13
     indépend
    1.05
     acides
    1.05
     informática
    1.03
    پيديا
    1.02
     enquête
    1.00
     insuffis
    0.98
     échanc
    0.97
     évidence
    0.96
     internationaux
    0.96
    Activations Density 0.000%

    No Known Activations