© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 78740
    Prev
    Next
    INDEX
    Explanations

    advancements in

    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_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
     изделий
    0.41
     basename
    0.40
    ฺ
    0.39
     Lees
    0.37
     Запад
    0.37
     преж
    0.37
    ตอน
    0.37
     mittlerweile
    0.37
     चुका
    0.36
     вирі
    0.36
    POSITIVE LOGITS
    Ţ
    0.40
    ắt
    0.40
     differenza
    0.38
     sains
    0.38
    स्त्री
    0.37
     woman
    0.37
     Ratt
    0.37
    检
    0.37
     ভাষায়
    0.36
     dall
    0.36
    Activations Density 0.005%

    No Known Activations