© 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. 40641
    Prev
    Next
    INDEX
    Explanations

    Korean and specific names

    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_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
     ky
    0.52
     metabol
    0.50
     ppl
    0.50
     goldfish
    0.49
     brute
    0.49
     β
    0.48
     heatmap
    0.48
     ),
    0.48
     ঘোষ
    0.48
     gelatin
    0.48
    POSITIVE LOGITS
    М
    0.61
    У
    0.61
    вы
    0.61
    ഏ
    0.60
    I
    0.58
    u
    0.55
    All
    0.55
     mengenai
    0.55
    ські
    0.54
    у
    0.54
    Activations Density 0.020%

    No Known Activations