© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173570
    Prev
    Next
    INDEX
    Explanations

    among groups and populations

    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_20_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
     특징
    0.21
     surfers
    0.17
    ၎င်း
    0.17
     Remarks
    0.17
    ंख
    0.16
     प्रतिनिध
    0.16
     uczest
    0.16
    䄳
    0.16
     চেষ্ট
    0.16
     ľudí
    0.16
    POSITIVE LOGITS
    ంటు
    0.20
    YL
    0.18
    yl
    0.18
     על
    0.17
    ceiver
    0.17
     vial
    0.16
     stalemate
    0.16
    mAb
    0.16
     unprecedented
    0.16
     rooted
    0.16
    Activations Density 0.002%

    No Known Activations