© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44280
    Prev
    Next
    INDEX
    Explanations

    visual representation

    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_3_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
    ﺎ
    0.82
    ی
    0.77
    ین
    0.70
    す
    0.70
    元の
    0.70
    パ
    0.68
     stvar
    0.67
    こだわ
    0.66
    ﻘ
    0.66
    ﻬ
    0.66
    POSITIVE LOGITS
    т
    0.89
    jší
    0.87
    ب
    0.78
    خدام
    0.78
     ومع
    0.71
    ت
    0.70
    ut
    0.69
    ва
    0.68
    ق
    0.67
    nelle
    0.66
    Activations Density 0.005%

    No Known Activations