© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 199144
    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_50_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
     hot
    0.44
    把握
    0.43
    hot
    0.41
    LD
    0.39
     боя
    0.39
     हॉट
    0.39
    枣
    0.39
     Hot
    0.38
     Diablo
    0.38
    ホット
    0.38
    POSITIVE LOGITS
    ِي
    0.42
    Chief
    0.39
    egir
    0.39
     Mile
    0.39
    Ç
    0.39
    Curtis
    0.38
    Ger
    0.38
    IsIn
    0.38
    ities
    0.38
    बास
    0.38
    Activations Density 0.000%

    No Known Activations