© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 215859
    Prev
    Next
    INDEX
    Explanations

    coke cinder

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_47_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
    CLOUD
    0.40
    鬥
    0.39
    ได
    0.37
    coord
    0.37
    Coord
    0.36
     পারস্প
    0.36
    Woods
    0.36
     Вайлд
    0.36
     affirme
    0.36
    ptu
    0.36
    POSITIVE LOGITS
     coke
    1.22
     c
    1.11
     Coke
    1.07
     cinder
    0.97
     кок
    0.89
     slag
    0.88
     ash
    0.80
     ص
    0.77
     ashes
    0.72
     cok
    0.72
    Activations Density 0.001%

    No Known Activations