© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145902
    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_0_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
    튜
    0.50
    <0x98>
    0.49
     Bournemouth
    0.49
    
    0.48
     souvenirs
    0.48
     rejuvenated
    0.48
     বাঙ্গালী
    0.48
     motore
    0.48
     veineux
    0.48
    ℍ
    0.48
    POSITIVE LOGITS
     Privat
    0.48
    Cre
    0.46
     готовы
    0.46
    cimento
    0.45
    ตอน
    0.45
    War
    0.44
    嵬
    0.44
    при
    0.43
    りが
    0.43
    Ready
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.