© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 66234
    Prev
    Next
    INDEX
    Explanations

    adjective endings

    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_51_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
     Sundance
    0.44
    }{-
    0.43
    㡷
    0.41
     किरायेदारों
    0.40
     साब
    0.40
     Williamson
    0.40
    慮
    0.40
     Willoughby
    0.39
     George
    0.38
    
    0.38
    POSITIVE LOGITS
    vel
    1.25
     vel
    1.23
    VEL
    1.23
    Vel
    1.20
     VEL
    1.20
     Vel
    1.15
    ivel
    1.02
    avel
    1.00
     velvet
    0.96
     Velvet
    0.96
    Activations Density 0.008%

    No Known Activations