© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9078
    Prev
    Next
    INDEX
    Explanations

    offshore wind, platforms, or islands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_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
     वापर
    0.31
     Số
    0.31
    繚
    0.29
     जेव्हा
    0.29
     Muitos
    0.29
     Recht
    0.28
    уд
    0.28
     Современ
    0.28
     Lorsque
    0.28
     Máy
    0.28
    POSITIVE LOGITS
    ق
    0.37
     offshore
    0.36
    ﻘ
    0.34
     island
    0.33
     دریا
    0.33
    de
    0.33
    m
    0.32
    島
    0.30
    岛
    0.30
    island
    0.29
    Activations Density 0.019%

    No Known Activations