© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10242
    Prev
    Next
    INDEX
    Explanations

    kpop members

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_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
    Hungary
    0.49
    妩
    0.48
     نظ
    0.47
     प्रवास
    0.47
    ने
    0.46
    ृत
    0.46
    Remove
    0.46
    Vol
    0.45
    Willow
    0.45
     शरद
    0.45
    POSITIVE LOGITS
     mangrove
    0.65
     d
    0.64
     Gonz
    0.63
    蚵
    0.63
     Galveston
    0.63
     Galapagos
    0.60
     fermion
    0.59
     Mombasa
    0.58
    鲅
    0.57
     plank
    0.57
    Activations Density 0.000%

    No Known Activations