© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 119019
    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_27_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
     WL
    0.40
    ]^
    0.39
    Autumn
    0.37
     inspiring
    0.36
     stimulating
    0.36
    정이
    0.36
    ⋙
    0.35
     انتظامی
    0.35
     Lang
    0.35
     outcomes
    0.34
    POSITIVE LOGITS
     일반적으로
    0.42
     एंगल
    0.41
     கோட்ப
    0.40
     noget
    0.38
     확실
    0.38
    窸
    0.38
     aspek
    0.38
     rebell
    0.37
    ële
    0.37
    Aqua
    0.37
    Activations Density 0.000%

    No Known Activations