© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 195583
    Prev
    Next
    INDEX
    Explanations

    deserts and rocks

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     gourd
    0.43
     होंगे
    0.40
    俅
    0.39
     కర్
    0.39
     Gour
    0.38
    פתח
    0.38
    的目标
    0.38
     Natasha
    0.38
    မ
    0.37
    的影响
    0.37
    POSITIVE LOGITS
     Nub
    0.54
     Ara
    0.52
     gravel
    0.47
     A
    0.46
    Nub
    0.44
     nub
    0.43
     Shay
    0.42
    Ara
    0.41
     frontiers
    0.40
     Sam
    0.40
    Activations Density 0.001%

    No Known Activations