© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 81479
    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
    
    0.52
     O
    0.46
     Sit
    0.43
     TK
    0.41
     Alt
    0.40
     Zy
    0.39
    Alt
    0.39
     Bez
    0.39
    Sit
    0.39
     Dul
    0.38
    POSITIVE LOGITS
    脏
    0.44
     fär
    0.38
    цин
    0.38
    гру
    0.37
    রন
    0.37
    городе
    0.37
    цер
    0.37
     سرا
    0.36
     නම්
    0.36
    fæ
    0.35
    Activations Density 0.000%

    No Known Activations