© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27725
    Prev
    Next
    INDEX
    Explanations

    route parameter integers

    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_10_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
     ।
    0.74
     обору
    0.66
     tomando
    0.65
     dañ
    0.65
     nCenters
    0.64
     ผล
    0.63
     mortem
    0.63
     nasz
    0.63
    第壹百
    0.63
    ।
    0.63
    POSITIVE LOGITS
    ע
    0.80
    ية
    0.79
    0
    0.77
    ﻟ
    0.76
    ى
    0.73
    斯
    0.73
    αν
    0.73
    سم
    0.71
    רי
    0.69
    يك
    0.68
    Activations Density 0.001%

    No Known Activations