© 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. 134270
    Prev
    Next
    INDEX
    Explanations

    training data

    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
     braiding
    0.48
     chute
    0.40
    lycer
    0.40
     waistcoat
    0.39
     stamping
    0.39
     rant
    0.38
     chur
    0.38
     नाखून
    0.38
    ᆸ
    0.38
     steamer
    0.38
    POSITIVE LOGITS
    CIO
    0.39
    SystemFileSystem
    0.39
     शेख
    0.38
     ko
    0.38
    वलं
    0.36
    駭
    0.36
    Latitude
    0.36
    ભાર
    0.35
    devkit
    0.35
     skil
    0.35
    Activations Density 0.003%

    No Known Activations