© 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
    2. Gemma-3-27B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 48281
    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_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
     жё
    0.54
    ב
    0.48
    ड
    0.46
     atm
    0.46
     overview
    0.46
     analyzing
    0.45
    2
    0.45
     imperme
    0.45
    ETTE
    0.44
    a
    0.44
    POSITIVE LOGITS
    scala
    0.45
    িল্লা
    0.44
     whis
    0.44
    rawy
    0.43
    ்துற
    0.42
     চলে
    0.42
     addCriterion
    0.41
     Balliye
    0.41
    wicz
    0.41
    rainian
    0.41
    Activations Density 0.000%

    No Known Activations