© 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. 3090
    Prev
    Next
    INDEX
    Explanations

    next chapter

    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
    寘
    0.38
    ั่ง
    0.37
    óny
    0.36
     waveform
    0.35
     termini
    0.35
    ⓪
    0.35
     terminations
    0.35
    थित
    0.35
    耧
    0.34
     sheared
    0.34
    POSITIVE LOGITS
     chapter
    3.05
     Chapter
    2.77
    Chapter
    2.63
    chapter
    2.63
     chapters
    2.61
     capítulo
    2.48
     Chapters
    2.34
     CHAPTER
    2.31
    chapters
    2.30
     chapitre
    2.25
    Activations Density 0.093%

    No Known Activations