© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    4. 195529
    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_4_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
    G
    0.60
    3
    0.57
    U
    0.56
    X
    0.56
    OD
    0.55
    6
    0.54
    Type
    0.52
    L
    0.52
    OC
    0.52
    Color
    0.50
    POSITIVE LOGITS
     utilisateur
    0.54
     responsables
    0.53
     faço
    0.51
     tentativas
    0.50
     centaines
    0.48
     getDate
    0.47
     effectuées
    0.47
     участие
    0.47
     κάν
    0.47
    詑
    0.47
    Activations Density 0.000%

    No Known Activations