© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 254077
    Prev
    Next
    INDEX
    Explanations

    class

    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_56_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
    ”]
    0.38
    social
    0.37
    ”:
    0.37
    sü
    0.36
     spliced
    0.35
    stractions
    0.35
    sizes
    0.35
    str
    0.34
    proofing
    0.34
    “
    0.34
    POSITIVE LOGITS
     Class
    1.09
     class
    1.03
    Class
    1.00
     classe
    0.98
     класс
    0.97
     Classe
    0.92
     clase
    0.91
     Classes
    0.89
     класса
    0.89
    Classe
    0.89
    Activations Density 0.000%

    No Known Activations