© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11311
    Prev
    Next
    INDEX
    Explanations

    Arabic word beginnings

    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_40_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
    <unused95>
    0.40
    ചര്യ
    0.37
    வனின்
    0.37
    cja
    0.37
    డంతో
    0.37
    தர
    0.36
    imaan
    0.36
    _="
    0.36
    ড়াল
    0.35
    defi
    0.35
    POSITIVE LOGITS
    すご
    0.38
    ன்னி
    0.38
    メモ
    0.37
    ::::::
    0.36
    杀
    0.36
    ,))
    0.36
    )\|
    0.35
    ساعدة
    0.35
     pomoći
    0.35
     Death
    0.34
    Activations Density 0.005%

    No Known Activations