© 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. 77194
    Prev
    Next
    INDEX
    Explanations

    cardinal directions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    сног
    0.43
     L
    0.42
     एक्सेल
    0.42
    篙
    0.42
    ηγ
    0.39
     מיי
    0.38
     Appellate
    0.38
    镑
    0.38
    Boys
    0.37
     ग्रीन
    0.36
    POSITIVE LOGITS
    North
    0.57
     North
    0.54
    West
    0.47
     West
    0.45
    北
    0.43
     WATTS
    0.41
    西
    0.41
     西
    0.40
     चिकित
    0.39
    derive
    0.39
    Activations Density 0.001%

    No Known Activations