© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 251213
    Prev
    Next
    INDEX
    Explanations

    runs

    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_56_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
     اتح
    0.39
     Kxf
    0.38
     offici
    0.37
    ꯃ
    0.36
    FBI
    0.36
     pinch
    0.35
     lb
    0.34
     لق
    0.34
    리에
    0.34
    एलबी
    0.34
    POSITIVE LOGITS
     runs
    2.83
     Runs
    2.59
    runs
    2.53
    Runs
    2.52
     रन
    1.07
     పరుగులు
    1.07
    跑
    1.06
     RUN
    1.01
     run
    0.99
     Run
    0.97
    Activations Density 0.009%

    No Known Activations