© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 19081
    Prev
    Next
    INDEX
    Explanations

    dual mics or plastic films

    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
    Negative Logits
    准备
    0.43
    IRCON
    0.40
     preparação
    0.38
    ⁠
    0.38
     WhatsApp
    0.37
    WhatsApp
    0.37
    ancher
    0.37
    prepare
    0.36
    準備
    0.35
     preparation
    0.34
    POSITIVE LOGITS
    ὑ
    0.47
     beau
    0.44
     Beau
    0.42
    Beau
    0.41
     pin
    0.41
     obiettivi
    0.40
    adati
    0.40
     ഉ
    0.40
    ပြီ
    0.38
     pied
    0.38
    Activations Density 0.015%

    No Known Activations