© 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. 59287
    Prev
    Next
    INDEX
    Explanations

    biodegradable, paradigm, paradise

    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
    1.63
    س
    1.62
    t
    1.45
    та
    1.41
    s
    1.40
    い
    1.37
    с
    1.34
    д
    1.28
    の色
    1.27
    的设计
    1.27
    POSITIVE LOGITS
    на
    1.45
    ہ
    1.11
    he
    1.09
    ร
    1.07
     deutschen
    1.02
    니다
    1.02
    న్స్‌
    1.00
     Odds
    0.98
    olet
    0.98
    urés
    0.97
    Activations Density 0.003%

    No Known Activations