© 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. 194718
    Prev
    Next
    INDEX
    Explanations

    storage

    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
    ossil
    0.46
     Stag
    0.46
     Sol
    0.44
     솔
    0.42
    Sol
    0.41
     sol
    0.40
    ભાગ
    0.40
     czyn
    0.40
     shim
    0.40
    stens
    0.40
    POSITIVE LOGITS
    কান্ত
    0.39
    办法
    0.37
     flake
    0.37
    Maxwell
    0.37
    ndo
    0.36
     Biochem
    0.36
    eské
    0.36
    ኡ
    0.36
    куда
    0.36
    quipe
    0.35
    Activations Density 0.000%

    No Known Activations