© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 198315
    Prev
    Next
    INDEX
    Explanations

    say "e" or "d" ending

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    зик
    0.38
    っぱり
    0.37
    amburg
    0.37
    }_\
    0.36
    OperationContext
    0.36
     PES
    0.35
     ez
    0.34
    irstrip
    0.34
    憶
    0.34
    licken
    0.34
    POSITIVE LOGITS
    ée
    1.08
    ee
    1.03
    ÉE
    0.96
    EE
    0.91
    ees
    0.91
    ées
    0.88
     ee
    0.88
    eee
    0.84
    Dee
    0.79
     Bee
    0.79
    Activations Density 0.018%

    No Known Activations