© 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. 36179
    Prev
    Next
    INDEX
    Explanations

    promotional emojis and phrases

    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
     وصلنا
    0.44
     দেখো
    0.43
     Спасибо
    0.38
    ḿ
    0.38
    esper
    0.37
    рма
    0.37
     দেখুন
    0.37
    諫
    0.37
    綘
    0.37
    劝
    0.37
    POSITIVE LOGITS
     superf
    0.43
     srand
    0.41
    seekg
    0.39
     subcl
    0.37
    GCD
    0.37
     millions
    0.36
     surging
    0.36
     kyl
    0.35
    ফিউ
    0.35
    秤
    0.35
    Activations Density 0.009%

    No Known Activations