© 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. 25018
    Prev
    Next
    INDEX
    Explanations

    ex prefix

    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
    ！)
    0.41
    ).\\
    0.39
    $.)
    0.39
    。）
    0.38
    )。
    0.38
    _)
    0.36
    )【
    0.34
     হ্
    0.34
    glasses
    0.34
    。)
    0.34
    POSITIVE LOGITS
     ex
    0.45
    edia
    0.35
     byl
    0.34
     exce
    0.34
     Ex
    0.34
     intim
    0.34
     svo
    0.33
     exon
    0.33
     gibi
    0.33
     lid
    0.33
    Activations Density 0.003%

    No Known Activations