© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35356
    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_11_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
    ,
    0.39
     future
    0.39
    ance
    0.38
    त्रा
    0.38
     часу
    0.38
    駿
    0.38
     हंगामा
    0.38
    resso
    0.38
    movie
    0.38
    attered
    0.37
    POSITIVE LOGITS
    ayın
    0.56
     invert
    0.52
     february
    0.52
    ০
    0.52
    ۟
    0.51
    意味着
    0.51
    锟
    0.51
    第一个
    0.49
     दिरहम
    0.49
    ன்மை
    0.49
    Activations Density 0.000%

    No Known Activations