© 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. 197906
    Prev
    Next
    INDEX
    Explanations

    bad

    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
    ͈
    0.53
    碖
    0.39
    ட்டிக்க
    0.39
    ливо
    0.38
    iliation
    0.36
     ख़
    0.36
     تبدی
    0.36
     이에
    0.36
    丰
    0.35
    ljiv
    0.35
    POSITIVE LOGITS
    ång
    0.45
     Bi
    0.43
     goss
    0.41
    uant
    0.39
    ospod
    0.39
    iring
    0.39
     fama
    0.39
     nn
    0.39
     biops
    0.39
     capo
    0.39
    Activations Density 0.000%

    No Known Activations