© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 157593
    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_50_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
    特
    0.40
    補助
    0.40
     বিগ
    0.40
    сер
    0.39
     Mem
    0.38
     Olympics
    0.38
    </table>
    0.37
    mem
    0.36
    เซอร์
    0.36
     סט
    0.35
    POSITIVE LOGITS
    As
    0.42
     चांगले
    0.41
     जाय
    0.40
    Ÿ
    0.39
     câteva
    0.39
    ಿಯೂ
    0.38
    ينه
    0.38
     যাত্রা
    0.37
    やや
    0.37
    andum
    0.37
    Activations Density 0.000%

    No Known Activations