© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16341
    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_40_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
    短期
    0.37
     대상
    0.37
     방
    0.36
     ಪರಿ
    0.36
    ovane
    0.34
    갱
    0.34
     পরিণ
    0.33
     변경
    0.33
     कदम
    0.33
    noindent
    0.32
    POSITIVE LOGITS
    샵
    0.39
    ificaciones
    0.38
    ഫ്
    0.38
     Negra
    0.38
     rng
    0.37
    灝
    0.37
     fichiers
    0.36
     bith
    0.36
     मचा
    0.35
    식회사
    0.34
    Activations Density 0.001%

    No Known Activations