© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 81080
    Prev
    Next
    INDEX
    Explanations

    Chinese phrases/slang

    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_53_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
    位
    0.48
    位的
    0.47
    EXE
    0.45
    幅度
    0.44
     nak
    0.42
    骚
    0.41
    Nak
    0.40
    少
    0.40
    ⎝
    0.39
    大的
    0.38
    POSITIVE LOGITS
     w
    0.40
     BASF
    0.37
     dp
    0.37
     раск
    0.37
     lay
    0.36
     رک
    0.36
     አሉ
    0.36
     patriot
    0.36
     rå
    0.36
     centimeters
    0.35
    Activations Density 0.003%

    No Known Activations