© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52048
    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
     overhead
    0.44
     sheaf
    0.43
    技術
    0.40
    िशा
    0.40
    amsung
    0.39
    overhead
    0.39
     Overhead
    0.38
    ệ
    0.37
    olution
    0.36
     NPTypeCode
    0.36
    POSITIVE LOGITS
     நாடுக
    0.40
    Dirt
    0.40
     dirt
    0.37
     ricost
    0.36
     Maltese
    0.35
     प्रजा
    0.35
     Died
    0.34
     Achievement
    0.34
     semej
    0.34
     Dirt
    0.34
    Activations Density 0.000%

    No Known Activations