© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4416
    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_40_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
    IQUE
    0.43
     directional
    0.39
    тона
    0.37
     Bhag
    0.37
     Deutsch
    0.37
     ರೂಪ
    0.36
     enquête
    0.36
     ഡ
    0.35
     й
    0.35
     రంగ
    0.35
    POSITIVE LOGITS
     après
    0.41
    Après
    0.40
     član
    0.39
    儘
    0.38
     Completely
    0.37
    mler
    0.37
    omores
    0.37
     dara
    0.36
    neigh
    0.36
    浼
    0.36
    Activations Density 0.000%

    No Known Activations