© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 9-GEMMASCOPE-2-TRANSCODER-262K
    4. 196863
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_9_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
    그
    0.65
    ue
    0.56
    ্ষ
    0.54
    at
    0.54
    <0xE1>
    0.52
    ಮ್
    0.51
    يد
    0.51
    جے
    0.50
    드를
    0.50
    ua
    0.49
    POSITIVE LOGITS
     Сы
    0.54
     Си
    0.51
    Limitations
    0.48
    kelijke
    0.47
    𝐅
    0.47
     обще
    0.47
    ]
    0.46
     प्
    0.46
    𝐕
    0.46
     Abortion
    0.46
    Activations Density 0.000%

    No Known Activations