© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 79610
    Prev
    Next
    INDEX
    Explanations

    sections breaking down categories

    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_29_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
     preservar
    0.38
    ِلِّ
    0.34
     travaillons
    0.33
     ਨਹੀਂ
    0.33
     belum
    0.33
    妗
    0.33
     ਵੀ
    0.32
    尚未
    0.32
     nejsou
    0.32
     এখনো
    0.32
    POSITIVE LOGITS
     González
    0.35
     Gordon
    0.35
     Tian
    0.35
    底部
    0.33
     Gonzalez
    0.32
     folgender
    0.32
     گوش
    0.32
    西方
    0.31
    Revolution
    0.31
    oncé
    0.31
    Activations Density 0.045%

    No Known Activations