© 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. 8579
    Prev
    Next
    INDEX
    Explanations

    Java 8 Streams

    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
    鏤
    0.39
     Koe
    0.38
    KeyUp
    0.38
    ರೇ
    0.38
    স্পতিবার
    0.38
     floor
    0.37
     Advisory
    0.37
     coincides
    0.37
     논
    0.36
    म्मीद
    0.35
    POSITIVE LOGITS
     вось
    0.52
    ၈
    0.50
    ८
    0.49
     acht
    0.48
     восем
    0.48
    ⁸
    0.47
    ders
    0.45
     eighth
    0.44
    第八
    0.43
     आठ
    0.43
    Activations Density 0.002%

    No Known Activations