© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130739
    Prev
    Next
    INDEX
    Explanations

    Yoon Suk-yeol

    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_6_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
    s
    1.30
    ле
    1.27
    س
    1.18
    ص
    1.14
    ir
    1.10
    it
    1.07
    ق
    1.07
    л
    1.05
    ف
    1.05
    ز
    1.02
    POSITIVE LOGITS
    কে
    1.01
    ﻞ
    0.98
    eria
    0.91
    ﺖ
    0.88
    Repository
    0.87
    Qatar
    0.83
    GB
    0.81
    ↵↵
    0.80
    PL
    0.80
    ﯽ
    0.80
    Activations Density 0.000%

    No Known Activations