© 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. 61833
    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
    𝗔
    0.59
    GLISH
    0.55
    ಾಪ
    0.55
    ='.$
    0.55
    면에
    0.53
    בת
    0.52
     प्लांट्स
    0.52
     앱
    0.52
    면
    0.52
    Ⅼ
    0.52
    POSITIVE LOGITS
     Pie
    0.56
     Pip
    0.53
     du
    0.52
     iç
    0.50
     this
    0.49
     BOL
    0.48
     MOM
    0.48
    τι
    0.47
     Atom
    0.47
     SMO
    0.46
    Activations Density 0.000%

    No Known Activations