© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 215603
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
     словами
    0.41
     сказал
    0.37
     сказала
    0.37
    왈
    0.37
     saying
    0.36
    सूत्र
    0.36
     pivot
    0.35
     powiedział
    0.35
     Saying
    0.35
    وز
    0.35
    POSITIVE LOGITS
     gestire
    0.40
     پھی
    0.39
     تخلی
    0.39
     iedere
    0.38
     احتاج
    0.38
     nơi
    0.38
    Ծ
    0.38
    每个人
    0.37
    誼
    0.37
     Tanzania
    0.37
    Activations Density 0.000%

    No Known Activations