© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 66172
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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_46_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
     ring
    0.86
     rings
    0.84
     Ring
    0.84
    Ring
    0.83
     Rings
    0.76
     RING
    0.73
    环
    0.72
     रिंग
    0.71
    環
    0.69
    リング
    0.68
    POSITIVE LOGITS
     கன்ன
    0.43
    )=(-
    0.40
    keydown
    0.40
    俶
    0.38
     Advisor
    0.38
     труда
    0.38
    塡
    0.38
     adv
    0.37
     ट्रेलर
    0.35
    Trees
    0.35
    Activations Density 0.038%

    No Known Activations