© 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. 198038
    Prev
    Next
    INDEX
    Explanations

    Heritage science, models

    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
     мора
    0.36
    jam
    0.36
    ඉ
    0.36
     initialise
    0.36
     tournament
    0.36
     analysing
    0.35
     науш
    0.35
    柯
    0.35
    Hib
    0.34
    eo
    0.34
    POSITIVE LOGITS
     Ruk
    0.42
    MERS
    0.41
     देखा
    0.41
    mers
    0.40
    telek
    0.40
     ruk
    0.40
     Ronda
    0.39
    BPACK
    0.38
     жовтня
    0.38
    ައް
    0.38
    Activations Density 0.000%

    No Known Activations