© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2145
    Prev
    Next
    INDEX
    Explanations

    investment in machinery

    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_39_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
     እየሱስ
    0.40
     menghad
    0.38
     الشع
    0.38
     École
    0.37
     margine
    0.36
     quadrada
    0.35
    एसआय
    0.35
    △
    0.35
     endroit
    0.35
     আয়নগুলি
    0.35
    POSITIVE LOGITS
     ছ
    0.36
    โน
    0.34
    سٹ
    0.34
    flu
    0.33
    Ir
    0.33
     Eman
    0.33
     செய்யப்பட்ட
    0.32
     беру
    0.32
     Helpline
    0.32
     Burk
    0.32
    Activations Density 0.002%

    No Known Activations