© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 219123
    Prev
    Next
    INDEX
    Explanations

    Māori and Hawaiian words

    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_31_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
    রণে
    0.36
     পালাতে
    0.36
    構成
    0.36
     Sain
    0.36
    服
    0.35
    觐
    0.35
    ispens
    0.35
     bentuk
    0.35
     compositional
    0.34
    July
    0.34
    POSITIVE LOGITS
     Māori
    0.43
    stuff
    0.41
    Lifecycle
    0.41
     glycoproteins
    0.39
    拉丁
    0.38
     lati
    0.38
     Ngọc
    0.38
    dib
    0.38
    坳
    0.38
     நியூ
    0.37
    Activations Density 0.001%

    No Known Activations