© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92800
    Prev
    Next
    INDEX
    Explanations

    hygeia, Guru, github, assembly

    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_11_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
    0.16
     moisture
    0.15
     M
    0.14
     hongkong
    0.14
     H
    0.14
     una
    0.14
     \
    0.14
     un
    0.14
     total
    0.14
     Osaka
    0.14
    POSITIVE LOGITS
    劻
    0.15
    人
    0.14
    ان
    0.13
    वेलकम
    0.13
    ਡ
    0.13
    人で
    0.13
    ieten
    0.12
    大脑
    0.12
    䔉
    0.12
    菪
    0.12
    Activations Density 0.000%

    No Known Activations