© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260326
    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
    เม
    0.46
    ６
    0.43
     жүктөө
    0.42
    ７
    0.42
     haem
    0.41
    ObjectTemp
    0.41
    waved
    0.41
    Scheduled
    0.41
    🕛
    0.41
     ночь
    0.40
    POSITIVE LOGITS
     appart
    0.46
     F
    0.45
     Vancouver
    0.43
     um
    0.41
     aux
    0.41
     alter
    0.41
     needle
    0.41
     multiplayer
    0.39
     painter
    0.39
     Dijkstra
    0.39
    Activations Density 0.000%

    No Known Activations