© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 115815
    Prev
    Next
    INDEX
    Explanations

    error and discount in formulas

    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_27_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
     softened
    0.38
    iktar
    0.37
    StringVar
    0.36
    ្
    0.35
    じて
    0.35
     dijadikan
    0.35
    geoning
    0.34
    atthena
    0.34
    ወስ
    0.34
    꺾
    0.34
    POSITIVE LOGITS
     мне
    0.44
     benefici
    0.40
    আমি
    0.40
     बताऊंगा
    0.38
     تقوم
    0.37
     আমিও
    0.37
    ロード
    0.37
    uré
    0.37
    屋外
    0.36
    屋内
    0.36
    Activations Density 0.004%

    No Known Activations