© 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. 164826
    Prev
    Next
    INDEX
    Explanations

    bright yellow

    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
     सोते
    0.38
    渶
    0.35
    дой
    0.34
     granic
    0.33
     ```
    0.33
    цата
    0.33
    vals
    0.33
    ,:)
    0.33
     নিক
    0.32
    Bingo
    0.32
    POSITIVE LOGITS
     sung
    0.35
    能量
    0.35
     पुरुष
    0.33
     oak
    0.33
     polished
    0.33
     vinyl
    0.32
     নিষ্ঠুর
    0.32
    Substitution
    0.32
    Чем
    0.31
    cra
    0.31
    Activations Density 0.006%

    No Known Activations