© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 51050
    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_30_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
     ແມ່ນ
    0.42
     каждого
    0.39
     आध्यात्मिक
    0.38
    久
    0.38
    生成
    0.38
     आधी
    0.37
     লজ্জা
    0.37
    ≃
    0.36
     শুক
    0.36
     seluruh
    0.36
    POSITIVE LOGITS
    羰
    0.38
    <unused51>
    0.36
     verification
    0.36
     regl
    0.35
    電機
    0.35
     enfermo
    0.35
     bipolar
    0.35
     ventilators
    0.35
     trifle
    0.34
     Regl
    0.34
    Activations Density 0.000%

    No Known Activations