© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 250356
    Prev
    Next
    INDEX
    Explanations

    Japanese text

    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
     쓰
    1.08
    ス
    0.95
     s
    0.93
     س
    0.93
    쓰
    0.93
     स
    0.92
     스
    0.90
     স
    0.89
    <0xAF>
    0.88
     ス
    0.86
    POSITIVE LOGITS
     th
    0.42
     thym
    0.41
    ஷ்ட
    0.40
    Hyp
    0.40
    Т
    0.39
    adhar
    0.38
    sht
    0.38
    ouf
    0.38
    etil
    0.37
    throp
    0.37
    Activations Density 0.002%

    No Known Activations