© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 101575
    Prev
    Next
    INDEX
    Explanations

    pieces, pawn, chess

    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_14_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
      
    0.52
    測
    0.46
    Oc
    0.44
    俄
    0.43
     Reflex
    0.43
     reflex
    0.42
     inst
    0.42
    鉐
    0.41
       
    0.41
    杷
    0.41
    POSITIVE LOGITS
     başında
    0.58
     dominates
    0.57
    ATIONAL
    0.55
     imasmim
    0.55
     करू
    0.53
     gł
    0.52
     mitologia
    0.50
     टाइ
    0.50
    committee
    0.50
     dominate
    0.49
    Activations Density 0.000%

    No Known Activations