© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 69360
    Prev
    Next
    INDEX
    Explanations

    leading zeros

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     Negotiation
    0.43
    挲
    0.38
     antioxidants
    0.37
    Ń
    0.36
     inteiro
    0.36
    Negoti
    0.35
     negotiators
    0.35
    钞
    0.34
     recebe
    0.34
    枪
    0.34
    POSITIVE LOGITS
     response
    0.38
     Jules
    0.38
     baffling
    0.38
     decimal
    0.38
     Twentieth
    0.38
     perplexing
    0.38
     Klu
    0.38
     моей
    0.37
    ",[(
    0.37
     Pledge
    0.37
    Activations Density 0.005%

    No Known Activations