© 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. 3504
    Prev
    Next
    INDEX
    Explanations

    caption generator

    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
     write
    0.50
     writing
    0.50
     لکھا
    0.48
     لکھ
    0.48
    写
    0.46
     writes
    0.45
     describ
    0.45
     written
    0.44
    WRITE
    0.44
    adin
    0.44
    POSITIVE LOGITS
     competitions
    0.43
     конкур
    0.40
     htmlentities
    0.40
     allemaal
    0.39
     संग्राम
    0.39
     portfolios
    0.39
    铮
    0.39
     конкурса
    0.39
    囦
    0.39
    ृत
    0.38
    Activations Density 0.008%

    No Known Activations