© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 134252
    Prev
    Next
    INDEX
    Explanations

    shoulder/riddle

    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_50_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
     Lone
    0.40
    S
    0.40
    持
    0.39
     Alejandro
    0.37
     Moore
    0.37
    Ihr
    0.37
     coil
    0.36
     Wade
    0.35
     Inhalte
    0.35
     ballast
    0.35
    POSITIVE LOGITS
     Shoulder
    0.54
     shoulder
    0.54
     Memorial
    0.51
    Memorial
    0.50
     ridd
    0.47
     Ridd
    0.46
    肩
    0.46
     riddle
    0.45
    shoulder
    0.44
     NOC
    0.43
    Activations Density 0.030%

    No Known Activations