© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 83094
    Prev
    Next
    INDEX
    Explanations

    Cons

    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_53_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
    藤
    0.39
    faulse
    0.38
    жба
    0.36
    敕
    0.36
     Iain
    0.35
     সৈয়দ
    0.34
    Fundamental
    0.33
     ),
    0.33
    UIViewController
    0.33
    ȝ
    0.33
    POSITIVE LOGITS
    textAllCaps
    0.35
     str
    0.35
     affinity
    0.34
     elevators
    0.34
     Rockies
    0.34
    np
    0.33
    শ্
    0.33
     страну
    0.33
    includes
    0.33
     clazz
    0.33
    Activations Density 0.001%

    No Known Activations