© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229728
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ון
    0.53
    ۳
    0.50
    อน
    0.49
    ﻚ
    0.49
    ्वती
    0.48
    ках
    0.48
    USER
    0.48
    ネス
    0.48
    วน
    0.47
    рі
    0.47
    POSITIVE LOGITS
    to
    0.71
    <unused60>
    0.68
    b
    0.66
    th
    0.66
    em
    0.65
    માં
    0.64
     étaient
    0.64
    is
    0.64
    ad
    0.64
     elétrica
    0.62
    Activations Density 0.000%

    No Known Activations