© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 93509
    Prev
    Next
    INDEX
    Explanations

    Chinese/Japanese names

    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_60_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
    历
    0.52
    歷
    0.46
    歴
    0.46
     served
    0.41
    伯
    0.41
    Insurance
    0.39
     Peu
    0.39
    曆
    0.39
    出
    0.39
     записи
    0.39
    POSITIVE LOGITS
    <0xE9>
    1.09
    才
    0.41
    熔
    0.41
    ultat
    0.39
    <0x83>
    0.39
     బ
    0.38
     methionine
    0.37
     же
    0.36
    랑
    0.36
    ว
    0.36
    Activations Density 0.003%

    No Known Activations