© 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. 32941
    Prev
    Next
    INDEX
    Explanations

    ding meaning or wordplay

    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
    Democratic
    0.39
     ~/
    0.39
    शक्ति
    0.38
     দোয়া
    0.38
     মান
    0.36
    ㄦ
    0.35
    无
    0.35
    沬
    0.34
    ᕝ
    0.34
     wordArray
    0.34
    POSITIVE LOGITS
     dictated
    0.39
     indict
    0.38
     guarded
    0.38
     guard
    0.37
     confidentiality
    0.37
     interpretation
    0.36
     bate
    0.36
     ura
    0.36
     outsiders
    0.36
     Corpo
    0.36
    Activations Density 0.001%

    No Known Activations