© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 175321
    Prev
    Next
    INDEX
    Explanations

    verb conjugation

    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_24_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
     نتیجے
    0.43
    ಾನ
    0.40
    glicherweise
    0.39
    йс
    0.38
     पदक
    0.38
     offseason
    0.38
    ﮢ
    0.38
     nonprofit
    0.37
     സമയ
    0.37
    锴
    0.37
    POSITIVE LOGITS
    口
    0.43
     बाय
    0.41
    قه
    0.40
    indeer
    0.39
    赤
    0.39
    ：
    0.39
    red
    0.39
     xix
    0.39
     aimer
    0.38
     Further
    0.38
    Activations Density 0.001%

    No Known Activations