© 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. 212912
    Prev
    Next
    INDEX
    Explanations

    URLs and websites

    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
     हा
    0.43
    茼
    0.42
    LinkForm
    0.41
    䨪
    0.40
    </footer>
    0.38
     quadrad
    0.38
     swirl
    0.38
    posure
    0.37
     Luch
    0.37
    ͞
    0.37
    POSITIVE LOGITS
    emonic
    0.44
    EM
    0.40
     patho
    0.40
    ifa
    0.40
    ViewModels
    0.40
    Sally
    0.40
     Kxg
    0.40
    ικής
    0.39
    DependentUpon
    0.39
     Freem
    0.39
    Activations Density 0.000%

    No Known Activations