© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218511
    Prev
    Next
    INDEX
    Explanations

    third-party cookies

    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
    tob
    0.47
    तला
    0.42
    óm
    0.39
    ával
    0.38
    acetamol
    0.38
    lá
    0.38
    ]]$
    0.38
    yb
    0.38
    णसी
    0.38
    reply
    0.37
    POSITIVE LOGITS
     Equ
    0.40
    各種
    0.38
    Equ
    0.36
     நிக
    0.36
    サラダ
    0.36
     കട
    0.36
     tang
    0.35
     मिलते
    0.35
     Perimeter
    0.35
    するもの
    0.34
    Activations Density 0.001%

    No Known Activations