© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157032
    Prev
    Next
    INDEX
    Explanations

    end of non-English 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_2_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
    し
    1.23
    ע
    1.20
    ร
    1.16
    도
    1.07
    l
    1.03
    もら
    1.02
    లు
    0.94
    าน
    0.86
    ุ
    0.85
    ется
    0.84
    POSITIVE LOGITS
    '
    1.05
    ция
    1.00
    的的
    1.00
    zt
    0.94
    zy
    0.94
    ı
    0.92
    い
    0.92
    та
    0.92
    كال
    0.91
    (
    0.89
    Activations Density 0.004%

    No Known Activations