© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18127
    Prev
    Next
    INDEX
    Explanations

    Owner, Director, Acquisitions, M&A, financial capital

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Error
    0.41
     Rhe
    0.41
     Aqu
    0.39
     Whyte
    0.38
     warmed
    0.37
    ចែកចាយ
    0.37
    撻
    0.37
     വെ
    0.37
     aqu
    0.36
     evil
    0.36
    POSITIVE LOGITS
     lelaki
    0.41
    olics
    0.40
    男性
    0.39
     কর্তৃত্ব
    0.37
    Lima
    0.37
    swedish
    0.37
    屐
    0.37
     transaksi
    0.36
    тали
    0.36
    üsü
    0.36
    Activations Density 0.033%

    No Known Activations