© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 81559
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    닼
    0.38
     तालुक
    0.37
    슷
    0.37
    㐰
    0.37
    στε
    0.36
     स्ट्रा
    0.35
    :";
    0.35
     assuming
    0.35
    ediakan
    0.35
     taman
    0.35
    POSITIVE LOGITS
    bulb
    0.40
     Clerk
    0.39
     bulbs
    0.38
     final
    0.38
    簀
    0.38
     Zoll
    0.38
    鲤
    0.37
    میری
    0.36
     ron
    0.36
     Final
    0.35
    Activations Density 0.000%

    No Known Activations