© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 162387
    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_31_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
     arred
    0.41
     userdata
    0.40
    िय
    0.39
     yanlış
    0.39
    compact
    0.38
     compact
    0.37
     locking
    0.37
    ẳ
    0.37
     ক্যারি
    0.37
    コンパクト
    0.37
    POSITIVE LOGITS
     উত্তেজ
    0.38
     அலு
    0.38
     établissements
    0.36
     })),
    0.36
     MPEG
    0.36
     அதி
    0.36
     dirigido
    0.35
    黝
    0.35
     premier
    0.34
     TIT
    0.34
    Activations Density 0.000%

    No Known Activations