© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26634
    Prev
    Next
    INDEX
    Explanations

    palindromic 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_10_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
    Λ
    0.56
    砷
    0.54
     Theories
    0.51
    گ
    0.51
    تو
    0.51
    Ç
    0.50
    اس
    0.49
    ع
    0.49
    八
    0.47
    لس
    0.47
    POSITIVE LOGITS
    jarige
    0.50
    zeigt
    0.48
    bik
    0.47
     necessitate
    0.47
     bài
    0.45
     leveled
    0.45
     пользователя
    0.45
     compañ
    0.45
    barred
    0.44
     majority
    0.44
    Activations Density 0.000%

    No Known Activations