© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 36682
    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_50_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
     رہی
    0.40
    信息化
    0.39
     Dying
    0.39
    Ἐ
    0.39
    ਈ
    0.38
     Rex
    0.38
     Stephenson
    0.38
     अध्यक्ष
    0.37
    ɖ
    0.37
    printDialog
    0.37
    POSITIVE LOGITS
    アダ
    0.40
    Petra
    0.40
     गा
    0.38
    रस
    0.36
     Horror
    0.36
    𝑧
    0.35
     гидро
    0.35
     ruộng
    0.35
    Min
    0.34
    awak
    0.34
    Activations Density 0.000%

    No Known Activations