© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 147047
    Prev
    Next
    INDEX
    Explanations

    prototype development

    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_18_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
    ەد
    0.46
    咱們
    0.46
    ﾇ
    0.45
    咱们
    0.45
     nefarious
    0.45
    团结
    0.45
    பாத
    0.45
     себя
    0.44
     سیاسی
    0.43
     sogenannten
    0.42
    POSITIVE LOGITS
     Strap
    0.55
     Report
    0.52
     streams
    0.52
     Stream
    0.52
     Males
    0.51
     Haven
    0.49
    體
    0.49
     Mild
    0.49
     cif
    0.48
    Streams
    0.48
    Activations Density 0.002%

    No Known Activations