© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 207326
    Prev
    Next
    INDEX
    Explanations

    Okay

    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_56_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
     행
    1.39
    行
    1.26
    행
    1.24
     row
    1.08
    Row
    1.07
     行
    1.03
    row
    1.02
     hành
    1.01
     Row
    0.99
    行的
    0.93
    POSITIVE LOGITS
     k
    1.44
     к
    0.94
     ك
    0.93
     ক
    0.78
     क
    0.76
    k
    0.76
     ک
    0.75
     K
    0.73
     ק
    0.66
    𝒌
    0.62
    Activations Density 0.006%

    No Known Activations