© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 193617
    Prev
    Next
    INDEX
    Explanations

    links to html download pages

    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_15_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    fortunate
    0.51
    𝐍
    0.50
     Charming
    0.50
     therefrom
    0.50
     egregious
    0.47
     ಪೂರ್ವ
    0.47
    ዛ
    0.47
    ing
    0.47
     इटावा
    0.47
     empt
    0.47
    POSITIVE LOGITS
    咯
    0.51
    一個
    0.50
    反應
    0.49
    Milliseconds
    0.45
    Res
    0.45
    淘汰
    0.45
    Reactive
    0.45
    对话
    0.44
     license
    0.43
    意识
    0.43
    Activations Density 0.000%

    No Known Activations