© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37665
    Prev
    Next
    INDEX
    Explanations

    you (various languages)

    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_57_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
    Tu
    0.47
    ﻦ
    0.43
     Tu
    0.42
    িন
    0.41
     نی
    0.40
     ни
    0.39
    atu
    0.39
    Ni
    0.39
    您的
    0.39
     Tufts
    0.39
    POSITIVE LOGITS
     u
    1.05
    Ip
    0.71
    ips
    0.68
     Ip
    0.66
    ip
    0.64
    IPS
    0.61
     उ
    0.61
    U
    0.60
    IP
    0.58
     ip
    0.58
    Activations Density 0.000%

    No Known Activations