© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    4. 260656
    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_22_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
    hattim
    0.56
     déprimées
    0.54
     आयोजित
    0.52
    秾
    0.51
     perí
    0.51
    VisualStyle
    0.50
    nfasis
    0.50
     ಇದೆ
    0.50
    䡓
    0.50
    艨
    0.50
    POSITIVE LOGITS
     can
    0.66
     [
    0.65
    i
    0.63
     global
    0.55
     former
    0.53
     pot
    0.52
    र
    0.52
     would
    0.52
     who
    0.51
     local
    0.51
    Activations Density 0.000%

    No Known Activations