© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 65007
    Prev
    Next
    INDEX
    Explanations

    ed

    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
    Negative Logits
    Jay
    0.39
     Grizzlies
    0.38
    reeting
    0.38
    nosis
    0.38
    iscale
    0.37
    legen
    0.37
    auri
    0.37
    嵓
    0.37
    ंत्रिकी
    0.36
    rej
    0.36
    POSITIVE LOGITS
     cert
    0.63
     certi
    0.50
     Cert
    0.45
     SUD
    0.42
     Selatan
    0.41
    Cert
    0.40
    cert
    0.39
     Zert
    0.38
     BA
    0.38
    SubDirectoryPath
    0.37
    Activations Density 0.002%

    No Known Activations