© 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. 34940
    Prev
    Next
    INDEX
    Explanations

    mixing bowls and ingredients

    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
     കഴ
    0.40
     eil
    0.38
    ılı
    0.37
     ㅛ
    0.37
    ÿ
    0.37
    菁
    0.36
    ည်
    0.36
    用餐
    0.36
     разрабо
    0.35
     tüket
    0.35
    POSITIVE LOGITS
     stirring
    0.51
     Stir
    0.51
     mixer
    0.48
     stirred
    0.47
     mixing
    0.45
     stirs
    0.45
     stirrer
    0.44
     Cooking
    0.43
     ingredients
    0.43
     Ingredients
    0.43
    Activations Density 0.132%

    No Known Activations