© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 139765
    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_46_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
    AddItem
    0.43
    hesis
    0.42
    jed
    0.37
    ĥ
    0.37
     mine
    0.37
     ours
    0.37
     firmly
    0.37
     jed
    0.36
    из
    0.36
     फिसल
    0.36
    POSITIVE LOGITS
    VOR
    0.41
    Ej
    0.38
    atoire
    0.38
     CODE
    0.38
     Weather
    0.38
     Selamat
    0.38
    ﻉ
    0.37
     воро
    0.37
    بلو
    0.37
    TableHeader
    0.37
    Activations Density 0.000%

    No Known Activations