© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 60575
    Prev
    Next
    INDEX
    Explanations

    expert / guru

    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_59_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
     an
    1.48
     الخ
    1.23
     خ
    1.16
     kh
    0.88
     ख
    0.82
    خ
    0.82
     Kh
    0.76
    Kh
    0.75
     খ
    0.69
    kh
    0.64
    POSITIVE LOGITS
     Guru
    0.98
     guru
    0.85
     Expert
    0.84
     गुरु
    0.80
    Expert
    0.79
     expert
    0.78
    Guru
    0.77
    guru
    0.74
     Whisper
    0.74
     whisper
    0.71
    Activations Density 0.038%

    No Known Activations