© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 74497
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
     Guant
    0.41
    扯
    0.39
     diamond
    0.39
    Platinum
    0.38
    PLAT
    0.36
     طور
    0.35
    jLabel
    0.35
    딱
    0.35
     choker
    0.35
    Sierra
    0.34
    POSITIVE LOGITS
     posao
    0.43
    ümüzde
    0.42
     unused
    0.42
     Queue
    0.42
    sett
    0.42
    ojen
    0.41
    queue
    0.40
    volunteer
    0.40
     settle
    0.40
    ವಾ
    0.40
    Activations Density 0.000%

    No Known Activations