© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 3083
    Prev
    Next
    INDEX
    Explanations

    **abstract** and **introduction**

    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_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
     chapter
    0.95
     Chapter
    0.89
     chapters
    0.85
    Chapter
    0.84
    chapters
    0.82
    chapter
    0.81
     Chapters
    0.81
    챕
    0.76
     CHAPTER
    0.74
     capítulo
    0.73
    POSITIVE LOGITS
     motivation
    0.63
     motivating
    0.63
     motiv
    0.61
     motivate
    0.59
     Motiv
    0.58
    motivation
    0.57
     motivación
    0.57
     motivations
    0.55
     motivates
    0.54
     motiva
    0.54
    Activations Density 0.025%

    No Known Activations