© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4912
    Prev
    Next
    INDEX
    Explanations

    model step by step

    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_40_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
    comput
    0.40
     computation
    0.40
    __.__
    0.39
     컴퓨
    0.38
     先
    0.38
     우선
    0.36
    computation
    0.36
    Computation
    0.35
    先
    0.35
     computational
    0.35
    POSITIVE LOGITS
     best
    0.40
     optimal
    0.38
     ideal
    0.37
     shoulders
    0.35
    っていました
    0.35
    最佳
    0.34
     सर्वश्रेष्ठ
    0.34
     channels
    0.33
     terbaik
    0.33
     بہترین
    0.33
    Activations Density 0.028%

    No Known Activations