© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 88657
    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_11_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
    de
    0.58
    c
    0.58
     George
    0.50
    s
    0.50
     from
    0.50
     J
    0.49
     trud
    0.49
    p
    0.48
     =
    0.48
    sn
    0.47
    POSITIVE LOGITS
     NLRP
    0.61
    '}}
    0.61
     Boltzmann
    0.60
    ponenten
    0.59
    zky
    0.58
    isine
    0.57
    plit
    0.57
     nonlinear
    0.56
     phasor
    0.55
    सीसीआई
    0.55
    Activations Density 0.000%

    No Known Activations