© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 3880
    Prev
    Next
    INDEX
    Explanations

    What

    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_44_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
    蕊
    0.43
    ﹚
    0.40
    ሚ
    0.39
     가능한
    0.39
     aux
    0.39
    停车
    0.38
     получает
    0.37
    znak
    0.37
    ▒
    0.37
    lastName
    0.37
    POSITIVE LOGITS
     exercises
    0.67
     Exercises
    0.57
     ejercicios
    0.55
     Exercise
    0.53
     exercise
    0.52
    Exercises
    0.52
     esercizi
    0.52
     challenges
    0.50
    challenges
    0.50
     Challenge
    0.50
    Activations Density 0.034%

    No Known Activations