© 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. 241443
    Prev
    Next
    INDEX
    Explanations

    Casimir Effect

    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
     لیګ
    0.37
    havi
    0.37
    Holding
    0.37
    ையா
    0.37
    ավոր
    0.37
    ]={
    0.36
    Deposit
    0.35
    俘
    0.35
     位
    0.34
     Cavan
    0.34
    POSITIVE LOGITS
     typed
    0.36
    ifr
    0.35
    dwm
    0.35
    태
    0.35
    <0xB8>
    0.34
     करी
    0.34
    ําน
    0.33
    தான
    0.33
     RID
    0.33
     ANS
    0.33
    Activations Density 0.001%

    No Known Activations