© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27878
    Prev
    Next
    INDEX
    Explanations

    personalities, model, man, journey

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_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
     teórico
    0.24
     atthakath
    0.22
     Naf
    0.21
     strengthen
    0.21
     ﺍﻟ
    0.21
     fortal
    0.20
    Ｄ
    0.20
    aba
    0.19
     ד
    0.19
    Dependency
    0.19
    POSITIVE LOGITS
    ра
    0.28
     poslov
    0.23
    ukuran
    0.22
    را
    0.22
    essero
    0.22
     unab
    0.21
    jeuner
    0.21
     acumen
    0.21
     toasts
    0.21
    ventana
    0.21
    Activations Density 0.004%

    No Known Activations