© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166559
    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_31_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
     സ്ഥാന
    0.39
    StarGo
    0.38
     positional
    0.37
    骼
    0.37
     frag
    0.36
    গো
    0.35
    POSIX
    0.35
     stratigraphic
    0.35
    mäß
    0.35
     maxValue
    0.34
    POSITIVE LOGITS
    晦
    0.40
     দুদ
    0.38
    ूद
    0.38
     Dedu
    0.37
     allere
    0.37
     दोनों
    0.36
    昅
    0.36
     दत्त
    0.36
     बल्ले
    0.35
    Architect
    0.35
    Activations Density 0.000%

    No Known Activations